R Notebook
This is an R Markdown Notebook. When you execute code within the notebook, the results appear beneath the code.
Try executing this chunk by clicking the Run button within the chunk or by placing your cursor inside it and pressing Cmd+Shift+Enter.
library(tidyverse)## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.4.0 ✔ purrr 0.3.5
## ✔ tibble 3.1.8 ✔ dplyr 1.0.10
## ✔ tidyr 1.2.1 ✔ stringr 1.4.1
## ✔ readr 2.1.3 ✔ forcats 0.5.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()library(readxl)
rm(list = ls())
disparity=read_csv("./race.csv", col_types = "ccdddd")## Warning: One or more parsing issues, call `problems()` on your data frame for details,
## e.g.:
## dat <- vroom(...)
## problems(dat)disparity$FIPS=substr(disparity$GEO_ID, 10, 14)
disparity$blwt=disparity$S1701_C03_010E - disparity$S1701_C03_009E
disparity$hpnon=disparity$S1701_C03_016E - disparity$S1701_C03_017E
tomerge=disparity[c(7:9)]
load("analytic3FIPS.RData")
analyticwrace=merge(analytic3, tomerge, by.x="FIPS", by.y="FIPS")
analyticwrace = na.omit(analyticwrace)
analyticwrace = analyticwrace[-1]#YPLL
library(caret)## Loading required package: lattice##
## Attaching package: 'caret'## The following object is masked from 'package:purrr':
##
## liftlibrary(xgboost)##
## Attaching package: 'xgboost'## The following object is masked from 'package:dplyr':
##
## slicelibrary(plyr)## ------------------------------------------------------------------------------## You have loaded plyr after dplyr - this is likely to cause problems.
## If you need functions from both plyr and dplyr, please load plyr first, then dplyr:
## library(plyr); library(dplyr)## ------------------------------------------------------------------------------##
## Attaching package: 'plyr'## The following objects are masked from 'package:dplyr':
##
## arrange, count, desc, failwith, id, mutate, rename, summarise,
## summarize## The following object is masked from 'package:purrr':
##
## compactlibrary(doParallel)## Loading required package: foreach##
## Attaching package: 'foreach'## The following objects are masked from 'package:purrr':
##
## accumulate, when## Loading required package: iterators## Loading required package: parallellibrary(pdp)##
## Attaching package: 'pdp'## The following object is masked from 'package:purrr':
##
## partialset.seed (1)
YPLLanalytic=analyticwrace[-c(2,3,4)]
nc = parallel::detectCores()
cl = makePSOCKcluster(nc-1) # Set number of cores equal to machine number minus one
registerDoParallel(cl) #Set up parallel
inTraining = createDataPartition(YPLLanalytic$YPLLdif, p = .75, list = FALSE)
training = YPLLanalytic[ inTraining,]
testing = YPLLanalytic[-inTraining,]
fitControl = trainControl(method = "repeatedcv",
number = 10,
repeats = 10,
allowParallel=TRUE
)
xgbGrid1 = expand.grid(nrounds = c(25, 50, 100, 200), #200, 300
max_depth = c(1, 2, 3), #2, 4, 6
eta = c(0.01, 0.025, 0.05), # 0.05, 0.075
gamma = 0,
colsample_bytree = c(0.8, 0.9, 1), #6, 7, 8
min_child_weight = 20,
subsample = c(0.8, 0.9, 1 )) #0.9, 1
xgbFit1 = train(YPLLdif ~ ., data = training,
method = "xgbTree",
trControl = fitControl,
tuneGrid = xgbGrid1,
nthread=1,
verbosity = 0
)
stopCluster(cl)
plot(varImp(xgbFit1))
vi=varImp(xgbFit1)
vi$importancexgbFit1## eXtreme Gradient Boosting
##
## 1472 samples
## 18 predictor
##
## No pre-processing
## Resampling: Cross-Validated (10 fold, repeated 10 times)
## Summary of sample sizes: 1326, 1325, 1324, 1325, 1325, 1325, ...
## Resampling results across tuning parameters:
##
## eta max_depth colsample_bytree subsample nrounds RMSE
## 0.010 1 0.8 0.8 25 1043.3201
## 0.010 1 0.8 0.8 50 1016.0238
## 0.010 1 0.8 0.8 100 988.8720
## 0.010 1 0.8 0.8 200 975.6898
## 0.010 1 0.8 0.9 25 1043.2085
## 0.010 1 0.8 0.9 50 1015.9154
## 0.010 1 0.8 0.9 100 988.5929
## 0.010 1 0.8 0.9 200 975.4487
## 0.010 1 0.8 1.0 25 1043.1847
## 0.010 1 0.8 1.0 50 1016.0793
## 0.010 1 0.8 1.0 100 988.5884
## 0.010 1 0.8 1.0 200 975.2774
## 0.010 1 0.9 0.8 25 1043.2662
## 0.010 1 0.9 0.8 50 1016.0727
## 0.010 1 0.9 0.8 100 988.8100
## 0.010 1 0.9 0.8 200 975.8062
## 0.010 1 0.9 0.9 25 1043.2153
## 0.010 1 0.9 0.9 50 1015.9244
## 0.010 1 0.9 0.9 100 988.5511
## 0.010 1 0.9 0.9 200 975.5253
## 0.010 1 0.9 1.0 25 1043.1952
## 0.010 1 0.9 1.0 50 1016.0930
## 0.010 1 0.9 1.0 100 988.6024
## 0.010 1 0.9 1.0 200 975.2864
## 0.010 1 1.0 0.8 25 1043.3452
## 0.010 1 1.0 0.8 50 1016.0753
## 0.010 1 1.0 0.8 100 988.8204
## 0.010 1 1.0 0.8 200 975.8297
## 0.010 1 1.0 0.9 25 1043.1853
## 0.010 1 1.0 0.9 50 1015.9640
## 0.010 1 1.0 0.9 100 988.6200
## 0.010 1 1.0 0.9 200 975.6161
## 0.010 1 1.0 1.0 25 1043.2220
## 0.010 1 1.0 1.0 50 1016.1036
## 0.010 1 1.0 1.0 100 988.5978
## 0.010 1 1.0 1.0 200 975.2873
## 0.010 2 0.8 0.8 25 1042.8383
## 0.010 2 0.8 0.8 50 1015.5289
## 0.010 2 0.8 0.8 100 988.9326
## 0.010 2 0.8 0.8 200 977.4068
## 0.010 2 0.8 0.9 25 1042.6150
## 0.010 2 0.8 0.9 50 1015.2800
## 0.010 2 0.8 0.9 100 988.5978
## 0.010 2 0.8 0.9 200 977.4132
## 0.010 2 0.8 1.0 25 1042.7558
## 0.010 2 0.8 1.0 50 1015.2862
## 0.010 2 0.8 1.0 100 988.3245
## 0.010 2 0.8 1.0 200 976.8890
## 0.010 2 0.9 0.8 25 1042.9306
## 0.010 2 0.9 0.8 50 1015.5206
## 0.010 2 0.9 0.8 100 989.0126
## 0.010 2 0.9 0.8 200 977.9637
## 0.010 2 0.9 0.9 25 1042.5773
## 0.010 2 0.9 0.9 50 1015.1955
## 0.010 2 0.9 0.9 100 988.6754
## 0.010 2 0.9 0.9 200 977.6194
## 0.010 2 0.9 1.0 25 1042.6909
## 0.010 2 0.9 1.0 50 1015.2499
## 0.010 2 0.9 1.0 100 988.3319
## 0.010 2 0.9 1.0 200 977.0038
## 0.010 2 1.0 0.8 25 1042.6143
## 0.010 2 1.0 0.8 50 1015.3502
## 0.010 2 1.0 0.8 100 988.9652
## 0.010 2 1.0 0.8 200 977.7379
## 0.010 2 1.0 0.9 25 1042.5574
## 0.010 2 1.0 0.9 50 1015.2080
## 0.010 2 1.0 0.9 100 988.5770
## 0.010 2 1.0 0.9 200 977.5720
## 0.010 2 1.0 1.0 25 1042.6169
## 0.010 2 1.0 1.0 50 1015.1912
## 0.010 2 1.0 1.0 100 988.3130
## 0.010 2 1.0 1.0 200 977.0064
## 0.010 3 0.8 0.8 25 1042.9221
## 0.010 3 0.8 0.8 50 1015.8554
## 0.010 3 0.8 0.8 100 989.9547
## 0.010 3 0.8 0.8 200 979.8628
## 0.010 3 0.8 0.9 25 1042.7594
## 0.010 3 0.8 0.9 50 1015.8373
## 0.010 3 0.8 0.9 100 990.1818
## 0.010 3 0.8 0.9 200 980.2329
## 0.010 3 0.8 1.0 25 1042.8025
## 0.010 3 0.8 1.0 50 1016.1196
## 0.010 3 0.8 1.0 100 990.9053
## 0.010 3 0.8 1.0 200 981.7181
## 0.010 3 0.9 0.8 25 1042.8241
## 0.010 3 0.9 0.8 50 1015.8243
## 0.010 3 0.9 0.8 100 990.1039
## 0.010 3 0.9 0.8 200 980.1990
## 0.010 3 0.9 0.9 25 1042.8103
## 0.010 3 0.9 0.9 50 1015.8606
## 0.010 3 0.9 0.9 100 990.2993
## 0.010 3 0.9 0.9 200 980.6399
## 0.010 3 0.9 1.0 25 1042.6710
## 0.010 3 0.9 1.0 50 1016.2182
## 0.010 3 0.9 1.0 100 991.1626
## 0.010 3 0.9 1.0 200 982.0122
## 0.010 3 1.0 0.8 25 1042.8077
## 0.010 3 1.0 0.8 50 1015.9416
## 0.010 3 1.0 0.8 100 990.3887
## 0.010 3 1.0 0.8 200 980.6814
## 0.010 3 1.0 0.9 25 1042.6231
## 0.010 3 1.0 0.9 50 1015.7909
## 0.010 3 1.0 0.9 100 990.5752
## 0.010 3 1.0 0.9 200 981.4853
## 0.010 3 1.0 1.0 25 1042.6602
## 0.010 3 1.0 1.0 50 1016.2208
## 0.010 3 1.0 1.0 100 991.3267
## 0.010 3 1.0 1.0 200 982.3791
## 0.025 1 0.8 0.8 25 1006.2605
## 0.025 1 0.8 0.8 50 982.4067
## 0.025 1 0.8 0.8 100 974.6974
## 0.025 1 0.8 0.8 200 976.7793
## 0.025 1 0.8 0.9 25 1005.9935
## 0.025 1 0.8 0.9 50 982.1496
## 0.025 1 0.8 0.9 100 974.6758
## 0.025 1 0.8 0.9 200 976.8648
## 0.025 1 0.8 1.0 25 1006.2745
## 0.025 1 0.8 1.0 50 981.9809
## 0.025 1 0.8 1.0 100 974.4651
## 0.025 1 0.8 1.0 200 976.3172
## 0.025 1 0.9 0.8 25 1006.3292
## 0.025 1 0.9 0.8 50 982.6467
## 0.025 1 0.9 0.8 100 974.9275
## 0.025 1 0.9 0.8 200 976.8067
## 0.025 1 0.9 0.9 25 1006.1729
## 0.025 1 0.9 0.9 50 982.1901
## 0.025 1 0.9 0.9 100 974.7691
## 0.025 1 0.9 0.9 200 976.8591
## 0.025 1 0.9 1.0 25 1006.2632
## 0.025 1 0.9 1.0 50 982.0041
## 0.025 1 0.9 1.0 100 974.4880
## 0.025 1 0.9 1.0 200 976.3247
## 0.025 1 1.0 0.8 25 1006.3598
## 0.025 1 1.0 0.8 50 982.7252
## 0.025 1 1.0 0.8 100 974.9940
## 0.025 1 1.0 0.8 200 976.8635
## 0.025 1 1.0 0.9 25 1006.1160
## 0.025 1 1.0 0.9 50 982.1137
## 0.025 1 1.0 0.9 100 974.7898
## 0.025 1 1.0 0.9 200 977.1033
## 0.025 1 1.0 1.0 25 1006.2644
## 0.025 1 1.0 1.0 50 982.0172
## 0.025 1 1.0 1.0 100 974.4926
## 0.025 1 1.0 1.0 200 976.3181
## 0.025 2 0.8 0.8 25 1005.9455
## 0.025 2 0.8 0.8 50 983.3638
## 0.025 2 0.8 0.8 100 977.5911
## 0.025 2 0.8 0.8 200 982.6016
## 0.025 2 0.8 0.9 25 1005.6716
## 0.025 2 0.8 0.9 50 982.9230
## 0.025 2 0.8 0.9 100 977.7772
## 0.025 2 0.8 0.9 200 982.3476
## 0.025 2 0.8 1.0 25 1005.5237
## 0.025 2 0.8 1.0 50 982.4412
## 0.025 2 0.8 1.0 100 976.8642
## 0.025 2 0.8 1.0 200 981.0821
## 0.025 2 0.9 0.8 25 1005.9851
## 0.025 2 0.9 0.8 50 983.2835
## 0.025 2 0.9 0.8 100 977.6276
## 0.025 2 0.9 0.8 200 983.2018
## 0.025 2 0.9 0.9 25 1005.5337
## 0.025 2 0.9 0.9 50 982.8047
## 0.025 2 0.9 0.9 100 977.6159
## 0.025 2 0.9 0.9 200 982.6418
## 0.025 2 0.9 1.0 25 1005.4040
## 0.025 2 0.9 1.0 50 982.4931
## 0.025 2 0.9 1.0 100 976.9144
## 0.025 2 0.9 1.0 200 981.0244
## 0.025 2 1.0 0.8 25 1005.6130
## 0.025 2 1.0 0.8 50 983.0676
## 0.025 2 1.0 0.8 100 978.0662
## 0.025 2 1.0 0.8 200 983.0544
## 0.025 2 1.0 0.9 25 1005.6049
## 0.025 2 1.0 0.9 50 982.7839
## 0.025 2 1.0 0.9 100 977.7146
## 0.025 2 1.0 0.9 200 982.8186
## 0.025 2 1.0 1.0 25 1005.3970
## 0.025 2 1.0 1.0 50 982.5599
## 0.025 2 1.0 1.0 100 977.0401
## 0.025 2 1.0 1.0 200 981.2244
## 0.025 3 0.8 0.8 25 1006.8196
## 0.025 3 0.8 0.8 50 984.5878
## 0.025 3 0.8 0.8 100 980.3547
## 0.025 3 0.8 0.8 200 988.2373
## 0.025 3 0.8 0.9 25 1006.5793
## 0.025 3 0.8 0.9 50 984.7079
## 0.025 3 0.8 0.9 100 981.1083
## 0.025 3 0.8 0.9 200 988.1965
## 0.025 3 0.8 1.0 25 1006.7457
## 0.025 3 0.8 1.0 50 985.6634
## 0.025 3 0.8 1.0 100 982.0407
## 0.025 3 0.8 1.0 200 987.9962
## 0.025 3 0.9 0.8 25 1006.3824
## 0.025 3 0.9 0.8 50 984.4023
## 0.025 3 0.9 0.8 100 980.3252
## 0.025 3 0.9 0.8 200 988.5004
## 0.025 3 0.9 0.9 25 1006.7133
## 0.025 3 0.9 0.9 50 985.6033
## 0.025 3 0.9 0.9 100 982.1276
## 0.025 3 0.9 0.9 200 989.4909
## 0.025 3 0.9 1.0 25 1006.8796
## 0.025 3 0.9 1.0 50 986.0146
## 0.025 3 0.9 1.0 100 982.4489
## 0.025 3 0.9 1.0 200 988.9907
## 0.025 3 1.0 0.8 25 1006.5529
## 0.025 3 1.0 0.8 50 985.2995
## 0.025 3 1.0 0.8 100 981.8786
## 0.025 3 1.0 0.8 200 989.7978
## 0.025 3 1.0 0.9 25 1006.3201
## 0.025 3 1.0 0.9 50 985.2903
## 0.025 3 1.0 0.9 100 982.5357
## 0.025 3 1.0 0.9 200 990.1615
## 0.025 3 1.0 1.0 25 1006.9083
## 0.025 3 1.0 1.0 50 986.3407
## 0.025 3 1.0 1.0 100 982.8622
## 0.025 3 1.0 1.0 200 989.0953
## 0.050 1 0.8 0.8 25 982.3022
## 0.050 1 0.8 0.8 50 974.9088
## 0.050 1 0.8 0.8 100 977.0615
## 0.050 1 0.8 0.8 200 981.4648
## 0.050 1 0.8 0.9 25 981.9512
## 0.050 1 0.8 0.9 50 974.5831
## 0.050 1 0.8 0.9 100 977.0311
## 0.050 1 0.8 0.9 200 980.7352
## 0.050 1 0.8 1.0 25 981.7293
## 0.050 1 0.8 1.0 50 974.4833
## 0.050 1 0.8 1.0 100 976.3785
## 0.050 1 0.8 1.0 200 979.3135
## 0.050 1 0.9 0.8 25 982.2232
## 0.050 1 0.9 0.8 50 974.9101
## 0.050 1 0.9 0.8 100 977.2793
## 0.050 1 0.9 0.8 200 981.7113
## 0.050 1 0.9 0.9 25 981.9255
## 0.050 1 0.9 0.9 50 974.9077
## 0.050 1 0.9 0.9 100 976.9658
## 0.050 1 0.9 0.9 200 980.6844
## 0.050 1 0.9 1.0 25 981.7277
## 0.050 1 0.9 1.0 50 974.5102
## 0.050 1 0.9 1.0 100 976.3583
## 0.050 1 0.9 1.0 200 979.3131
## 0.050 1 1.0 0.8 25 982.3191
## 0.050 1 1.0 0.8 50 975.2608
## 0.050 1 1.0 0.8 100 977.5200
## 0.050 1 1.0 0.8 200 981.7227
## 0.050 1 1.0 0.9 25 982.0065
## 0.050 1 1.0 0.9 50 974.5971
## 0.050 1 1.0 0.9 100 976.9508
## 0.050 1 1.0 0.9 200 980.9986
## 0.050 1 1.0 1.0 25 981.7371
## 0.050 1 1.0 1.0 50 974.5260
## 0.050 1 1.0 1.0 100 976.3576
## 0.050 1 1.0 1.0 200 979.3358
## 0.050 2 0.8 0.8 25 983.1828
## 0.050 2 0.8 0.8 50 978.3815
## 0.050 2 0.8 0.8 100 983.6458
## 0.050 2 0.8 0.8 200 994.0460
## 0.050 2 0.8 0.9 25 982.8825
## 0.050 2 0.8 0.9 50 977.9582
## 0.050 2 0.8 0.9 100 982.8875
## 0.050 2 0.8 0.9 200 992.0985
## 0.050 2 0.8 1.0 25 982.4232
## 0.050 2 0.8 1.0 50 977.0850
## 0.050 2 0.8 1.0 100 981.3809
## 0.050 2 0.8 1.0 200 988.3430
## 0.050 2 0.9 0.8 25 983.1034
## 0.050 2 0.9 0.8 50 978.4276
## 0.050 2 0.9 0.8 100 983.8292
## 0.050 2 0.9 0.8 200 993.1959
## 0.050 2 0.9 0.9 25 982.2343
## 0.050 2 0.9 0.9 50 977.3208
## 0.050 2 0.9 0.9 100 982.5898
## 0.050 2 0.9 0.9 200 992.0231
## 0.050 2 0.9 1.0 25 982.3446
## 0.050 2 0.9 1.0 50 976.8801
## 0.050 2 0.9 1.0 100 981.4398
## 0.050 2 0.9 1.0 200 989.2551
## 0.050 2 1.0 0.8 25 983.1735
## 0.050 2 1.0 0.8 50 978.1306
## 0.050 2 1.0 0.8 100 983.7053
## 0.050 2 1.0 0.8 200 994.1737
## 0.050 2 1.0 0.9 25 983.0445
## 0.050 2 1.0 0.9 50 978.2159
## 0.050 2 1.0 0.9 100 983.6465
## 0.050 2 1.0 0.9 200 992.9043
## 0.050 2 1.0 1.0 25 982.2422
## 0.050 2 1.0 1.0 50 977.2128
## 0.050 2 1.0 1.0 100 981.4683
## 0.050 2 1.0 1.0 200 989.3110
## 0.050 3 0.8 0.8 25 985.0324
## 0.050 3 0.8 0.8 50 980.8261
## 0.050 3 0.8 0.8 100 990.1261
## 0.050 3 0.8 0.8 200 1002.7329
## 0.050 3 0.8 0.9 25 984.5548
## 0.050 3 0.8 0.9 50 981.7452
## 0.050 3 0.8 0.9 100 989.1714
## 0.050 3 0.8 0.9 200 1002.5246
## 0.050 3 0.8 1.0 25 985.2814
## 0.050 3 0.8 1.0 50 981.9568
## 0.050 3 0.8 1.0 100 988.7007
## 0.050 3 0.8 1.0 200 1000.3670
## 0.050 3 0.9 0.8 25 985.1976
## 0.050 3 0.9 0.8 50 982.3036
## 0.050 3 0.9 0.8 100 990.6038
## 0.050 3 0.9 0.8 200 1004.3698
## 0.050 3 0.9 0.9 25 985.1100
## 0.050 3 0.9 0.9 50 982.9106
## 0.050 3 0.9 0.9 100 990.5090
## 0.050 3 0.9 0.9 200 1003.0302
## 0.050 3 0.9 1.0 25 985.9366
## 0.050 3 0.9 1.0 50 982.6268
## 0.050 3 0.9 1.0 100 988.9758
## 0.050 3 0.9 1.0 200 1001.5817
## 0.050 3 1.0 0.8 25 984.5702
## 0.050 3 1.0 0.8 50 981.5406
## 0.050 3 1.0 0.8 100 990.1069
## 0.050 3 1.0 0.8 200 1002.8954
## 0.050 3 1.0 0.9 25 985.1304
## 0.050 3 1.0 0.9 50 982.0662
## 0.050 3 1.0 0.9 100 990.0816
## 0.050 3 1.0 0.9 200 1002.8511
## 0.050 3 1.0 1.0 25 986.1594
## 0.050 3 1.0 1.0 50 982.7582
## 0.050 3 1.0 1.0 100 989.3500
## 0.050 3 1.0 1.0 200 1002.8899
## Rsquared MAE
## 0.018867431 762.9590
## 0.018503191 736.8657
## 0.017311546 712.1963
## 0.014682420 701.8233
## 0.018342539 762.8050
## 0.018238063 736.6727
## 0.017977047 711.9518
## 0.014926933 701.5248
## 0.016377245 762.7546
## 0.016450549 736.7052
## 0.017864325 711.8252
## 0.015264390 701.4299
## 0.017806484 762.8968
## 0.017397279 736.8750
## 0.016830348 712.1364
## 0.013865941 701.8543
## 0.017754407 762.8116
## 0.018087008 736.6763
## 0.018099494 711.8680
## 0.014819582 701.5702
## 0.015790218 762.7707
## 0.016457325 736.6983
## 0.017828865 711.8246
## 0.015215901 701.4354
## 0.017316281 762.9504
## 0.017418457 736.8947
## 0.016666393 712.1978
## 0.013920548 701.9864
## 0.017489839 762.7739
## 0.017610584 736.6976
## 0.017475464 711.9918
## 0.014491812 701.7200
## 0.015461492 762.7691
## 0.016429113 736.7046
## 0.017818352 711.8213
## 0.015229776 701.4334
## 0.017184633 762.2581
## 0.016276120 735.7871
## 0.014990117 711.0722
## 0.012405960 701.9566
## 0.017122634 762.1771
## 0.016539574 735.6590
## 0.015225396 710.8595
## 0.012275251 701.7218
## 0.014978135 762.2545
## 0.015914731 735.6773
## 0.015768313 710.4895
## 0.013382995 701.1061
## 0.014922081 762.2564
## 0.015663229 735.7013
## 0.014018928 711.0574
## 0.011307835 702.1564
## 0.016592946 762.0757
## 0.016334721 735.5724
## 0.014857712 710.7841
## 0.012009828 701.8143
## 0.014874117 762.2118
## 0.015887254 735.6263
## 0.015838451 710.4826
## 0.013174377 701.1876
## 0.016727375 762.0629
## 0.016079828 735.6175
## 0.014327141 710.9334
## 0.012128361 701.9071
## 0.016309773 762.0696
## 0.015902624 735.5823
## 0.014800082 710.7181
## 0.011930040 701.7762
## 0.015097392 762.1711
## 0.016095212 735.6187
## 0.016011197 710.4762
## 0.013337434 701.2639
## 0.014835162 761.9647
## 0.013514202 735.2728
## 0.012836397 710.4035
## 0.010982725 702.1595
## 0.015633127 761.8261
## 0.014081499 735.2875
## 0.012231673 710.5809
## 0.010965800 702.5391
## 0.015101997 761.8026
## 0.013839480 735.4318
## 0.012340626 710.9194
## 0.009932966 703.4982
## 0.014468693 761.8196
## 0.013445660 735.2278
## 0.012432545 710.5210
## 0.010792111 702.3254
## 0.014326821 761.7351
## 0.013401833 735.1919
## 0.012011517 710.6708
## 0.010605935 702.8084
## 0.015564056 761.6384
## 0.014008666 735.2730
## 0.012252351 710.8671
## 0.009814318 703.6559
## 0.013973046 761.7960
## 0.013113216 735.2816
## 0.011840243 710.8252
## 0.010162512 702.7319
## 0.015068224 761.5665
## 0.013781201 735.0656
## 0.011843534 710.7615
## 0.009945372 703.3173
## 0.015686689 761.6120
## 0.014089632 735.2572
## 0.012079584 711.0276
## 0.009729916 703.9692
## 0.017032417 728.0042
## 0.016021666 706.5590
## 0.013566612 701.7484
## 0.010609701 704.1437
## 0.018368442 727.6758
## 0.017007603 706.2762
## 0.013626445 701.7279
## 0.010471938 704.0288
## 0.016989193 727.7456
## 0.017776428 706.0932
## 0.013988995 701.4033
## 0.010816316 703.4133
## 0.016551215 728.0265
## 0.015695652 706.7421
## 0.013095666 702.0103
## 0.010826305 704.1936
## 0.017666764 727.8144
## 0.017242835 706.2900
## 0.013299193 701.7726
## 0.010272750 704.1165
## 0.017049959 727.7411
## 0.017735449 706.1339
## 0.013888155 701.4264
## 0.010780864 703.4223
## 0.017042654 727.9560
## 0.015546196 706.7107
## 0.012982656 701.9301
## 0.010865784 704.3430
## 0.017767539 727.7920
## 0.017212818 706.2954
## 0.013303618 701.7213
## 0.010400235 704.2105
## 0.017127300 727.7356
## 0.017679591 706.1354
## 0.013910553 701.4272
## 0.010807212 703.4081
## 0.014783865 726.9792
## 0.012955155 705.8738
## 0.011076943 702.3695
## 0.010367064 705.8772
## 0.015859433 726.5758
## 0.013381298 705.4100
## 0.010558930 702.3766
## 0.009554212 705.7304
## 0.015862626 726.5242
## 0.015091737 705.1461
## 0.012226042 701.7185
## 0.011105597 705.0942
## 0.014350970 726.8750
## 0.012782218 705.9177
## 0.011170874 702.6410
## 0.009656114 706.5884
## 0.015774220 726.5645
## 0.014400331 705.3513
## 0.011452008 702.3307
## 0.010508443 706.0381
## 0.016224396 726.4597
## 0.014991559 705.0986
## 0.011903491 701.7015
## 0.010819696 705.0091
## 0.015268954 726.5998
## 0.013637536 705.7682
## 0.010467951 702.7972
## 0.009418345 706.3132
## 0.015884368 726.5503
## 0.014531862 705.3082
## 0.011715539 702.3235
## 0.010328839 706.0939
## 0.016109771 726.4706
## 0.015065365 705.1997
## 0.012110952 701.7331
## 0.011287563 705.0773
## 0.012583422 726.3453
## 0.012202764 705.4698
## 0.010329775 703.0177
## 0.010090474 708.5948
## 0.013129849 726.2525
## 0.011871687 705.7005
## 0.010059810 703.5028
## 0.009455207 708.5913
## 0.013360613 726.1009
## 0.011548016 706.0696
## 0.009583570 704.0273
## 0.009547765 708.1758
## 0.014832585 726.0034
## 0.012678541 705.5474
## 0.010978516 702.8261
## 0.009578785 708.4251
## 0.012830789 726.2469
## 0.011126927 706.2721
## 0.009617937 704.3127
## 0.009044037 709.1001
## 0.013278829 726.2156
## 0.011207201 706.3075
## 0.009309790 704.1934
## 0.009438398 708.8036
## 0.013066994 725.9845
## 0.011045922 706.0023
## 0.009953818 704.0091
## 0.009211888 709.3828
## 0.012607250 725.8573
## 0.011058163 705.9428
## 0.009326638 704.5369
## 0.008629492 709.6943
## 0.013617662 726.2149
## 0.010871634 706.6154
## 0.009204251 704.8267
## 0.009534764 709.0217
## 0.016087016 706.5092
## 0.013315999 701.9783
## 0.010738933 704.4101
## 0.009841700 707.1963
## 0.016779489 706.0731
## 0.013994229 701.5850
## 0.010661689 703.9294
## 0.010461055 706.0192
## 0.017560358 705.8982
## 0.013793836 701.4415
## 0.010721459 703.4176
## 0.010788999 704.7931
## 0.015694504 706.3633
## 0.012710187 702.1407
## 0.010418528 704.5557
## 0.009815536 707.0451
## 0.016860298 706.1090
## 0.012888121 701.9157
## 0.010372826 704.2433
## 0.010032011 706.0193
## 0.017526077 705.8777
## 0.013750251 701.4395
## 0.010778464 703.3739
## 0.010694239 704.8005
## 0.015386634 706.4768
## 0.012252539 702.3600
## 0.010098672 704.5632
## 0.009815961 706.9755
## 0.016891578 706.2468
## 0.013815168 701.6835
## 0.010318677 704.1761
## 0.010158185 706.3739
## 0.017532715 705.8765
## 0.013756451 701.4608
## 0.010716155 703.3985
## 0.010695721 704.8197
## 0.012830021 706.0855
## 0.010623239 703.0231
## 0.009889052 706.9996
## 0.009476513 713.3739
## 0.013053371 705.6366
## 0.011131910 702.5984
## 0.009897737 705.7353
## 0.010376605 711.4454
## 0.014414865 705.1021
## 0.012052946 701.7848
## 0.010906622 705.3440
## 0.010478474 709.2462
## 0.012549421 705.7589
## 0.010392305 703.0363
## 0.009899763 707.2838
## 0.009760174 712.8075
## 0.014743372 705.0755
## 0.012140178 702.3517
## 0.010678234 706.2267
## 0.010423591 711.4776
## 0.014742613 705.0962
## 0.012255367 701.7733
## 0.011198934 705.2525
## 0.010382805 709.8727
## 0.013967484 705.4508
## 0.011563892 702.7790
## 0.009994686 706.5804
## 0.009272431 713.1399
## 0.013411861 705.6766
## 0.011274269 702.8670
## 0.010447261 706.9549
## 0.009949290 712.4235
## 0.015135292 705.0499
## 0.012019216 701.9944
## 0.011316172 705.3280
## 0.010373055 709.8571
## 0.010974262 705.8058
## 0.010934220 703.1812
## 0.009726018 709.4172
## 0.009120930 717.1935
## 0.012271379 705.9254
## 0.010263838 704.2990
## 0.009728698 709.7454
## 0.009522394 717.6769
## 0.012137361 705.9326
## 0.010284158 704.1749
## 0.009994362 708.9992
## 0.010188572 716.4035
## 0.010781444 706.1998
## 0.009866025 704.6312
## 0.009242143 709.9864
## 0.009293020 718.6889
## 0.010862098 705.6650
## 0.008476164 704.4094
## 0.009099263 709.7769
## 0.009108984 717.2911
## 0.011100187 706.1870
## 0.009160159 704.3293
## 0.009843136 708.7558
## 0.009702431 716.6192
## 0.013205131 705.5516
## 0.010960371 704.1256
## 0.010280070 709.9570
## 0.010417803 717.9079
## 0.011641393 705.8407
## 0.010679840 704.1803
## 0.009833062 710.1246
## 0.009574640 717.4771
## 0.011084196 706.5792
## 0.009710329 704.6889
## 0.009881654 709.3570
## 0.009909421 717.5688
##
## Tuning parameter 'gamma' was held constant at a value of 0
## Tuning
## parameter 'min_child_weight' was held constant at a value of 20
## RMSE was used to select the optimal model using the smallest value.
## The final values used for the model were nrounds = 100, max_depth = 1, eta
## = 0.025, gamma = 0, colsample_bytree = 0.8, min_child_weight = 20
## and subsample = 1.plot(xgbFit1)
# mental
library(caret)
library(xgboost)
library(plyr)
library(doParallel)
library(pdp)
set.seed (1)
mentalanalytic=analyticwrace[-c(1,3,4)]
nc = parallel::detectCores()
cl = makePSOCKcluster(nc-1) # Set number of cores equal to machine number minus one
registerDoParallel(cl) #Set up parallel
inTraining = createDataPartition(mentalanalytic$mentaldif, p = .75, list = FALSE)
training = mentalanalytic[ inTraining,]
testing = mentalanalytic[-inTraining,]
fitControl = trainControl(method = "repeatedcv",
number = 10,
repeats = 10,
allowParallel=TRUE
)
xgbGrid2 = expand.grid(nrounds = c(25, 50, 100, 200), #200, 300
max_depth = c(1, 2, 3), #2, 4, 6
eta = c(0.01, 0.025, 0.05), # 0.05, 0.075
gamma = 0,
colsample_bytree = c(0.8, 0.9, 1), #6, 7, 8
min_child_weight = 20,
subsample = c(0.8, 0.9, 1 )) #0.9, 1
xgbFit2 = train(mentaldif ~ ., data = training,
method = "xgbTree",
trControl = fitControl,
tuneGrid = xgbGrid2,
nthread=1,
verbosity = 0
)
stopCluster(cl)
plot(varImp(xgbFit2)) 
vi=varImp(xgbFit2)
vi$importancexgbFit2## eXtreme Gradient Boosting
##
## 1472 samples
## 18 predictor
##
## No pre-processing
## Resampling: Cross-Validated (10 fold, repeated 10 times)
## Summary of sample sizes: 1326, 1325, 1324, 1325, 1325, 1325, ...
## Resampling results across tuning parameters:
##
## eta max_depth colsample_bytree subsample nrounds RMSE Rsquared
## 0.010 1 0.8 0.8 25 0.7451590 0.03173981
## 0.010 1 0.8 0.8 50 0.7411762 0.03178692
## 0.010 1 0.8 0.8 100 0.7370817 0.03381451
## 0.010 1 0.8 0.8 200 0.7336505 0.03818719
## 0.010 1 0.8 0.9 25 0.7450453 0.03163443
## 0.010 1 0.8 0.9 50 0.7410360 0.03165514
## 0.010 1 0.8 0.9 100 0.7371613 0.03267773
## 0.010 1 0.8 0.9 200 0.7339573 0.03669814
## 0.010 1 0.8 1.0 25 0.7448753 0.03196838
## 0.010 1 0.8 1.0 50 0.7409363 0.03089942
## 0.010 1 0.8 1.0 100 0.7373616 0.03095173
## 0.010 1 0.8 1.0 200 0.7343961 0.03524175
## 0.010 1 0.9 0.8 25 0.7451464 0.03099881
## 0.010 1 0.9 0.8 50 0.7411850 0.03109893
## 0.010 1 0.9 0.8 100 0.7370952 0.03327362
## 0.010 1 0.9 0.8 200 0.7336695 0.03756330
## 0.010 1 0.9 0.9 25 0.7450312 0.03064773
## 0.010 1 0.9 0.9 50 0.7410465 0.03104795
## 0.010 1 0.9 0.9 100 0.7371641 0.03273966
## 0.010 1 0.9 0.9 200 0.7338202 0.03743213
## 0.010 1 0.9 1.0 25 0.7448915 0.03084124
## 0.010 1 0.9 1.0 50 0.7409510 0.03061155
## 0.010 1 0.9 1.0 100 0.7373661 0.03092887
## 0.010 1 0.9 1.0 200 0.7343990 0.03522819
## 0.010 1 1.0 0.8 25 0.7451298 0.03042025
## 0.010 1 1.0 0.8 50 0.7411453 0.03109672
## 0.010 1 1.0 0.8 100 0.7371013 0.03316181
## 0.010 1 1.0 0.8 200 0.7336045 0.03808991
## 0.010 1 1.0 0.9 25 0.7450428 0.03019713
## 0.010 1 1.0 0.9 50 0.7410980 0.03055456
## 0.010 1 1.0 0.9 100 0.7372341 0.03199913
## 0.010 1 1.0 0.9 200 0.7339463 0.03664681
## 0.010 1 1.0 1.0 25 0.7449369 0.02982916
## 0.010 1 1.0 1.0 50 0.7409712 0.03039340
## 0.010 1 1.0 1.0 100 0.7373649 0.03095583
## 0.010 1 1.0 1.0 200 0.7344012 0.03522067
## 0.010 2 0.8 0.8 25 0.7434801 0.04364163
## 0.010 2 0.8 0.8 50 0.7379031 0.04794235
## 0.010 2 0.8 0.8 100 0.7313004 0.05370018
## 0.010 2 0.8 0.8 200 0.7250756 0.06161464
## 0.010 2 0.8 0.9 25 0.7434140 0.04187534
## 0.010 2 0.8 0.9 50 0.7380196 0.04479293
## 0.010 2 0.8 0.9 100 0.7314551 0.05195959
## 0.010 2 0.8 0.9 200 0.7251787 0.06104700
## 0.010 2 0.8 1.0 25 0.7434676 0.03898372
## 0.010 2 0.8 1.0 50 0.7381633 0.04120492
## 0.010 2 0.8 1.0 100 0.7316832 0.04996723
## 0.010 2 0.8 1.0 200 0.7252927 0.06049305
## 0.010 2 0.9 0.8 25 0.7434535 0.04204099
## 0.010 2 0.9 0.8 50 0.7379655 0.04642096
## 0.010 2 0.9 0.8 100 0.7313804 0.05284964
## 0.010 2 0.9 0.8 200 0.7248543 0.06217268
## 0.010 2 0.9 0.9 25 0.7434795 0.03978562
## 0.010 2 0.9 0.9 50 0.7381264 0.04304838
## 0.010 2 0.9 0.9 100 0.7314112 0.05169777
## 0.010 2 0.9 0.9 200 0.7250609 0.06096291
## 0.010 2 0.9 1.0 25 0.7435406 0.03656768
## 0.010 2 0.9 1.0 50 0.7382364 0.03993162
## 0.010 2 0.9 1.0 100 0.7317041 0.04986194
## 0.010 2 0.9 1.0 200 0.7250640 0.06131157
## 0.010 2 1.0 0.8 25 0.7433059 0.04210015
## 0.010 2 1.0 0.8 50 0.7378351 0.04635474
## 0.010 2 1.0 0.8 100 0.7311095 0.05381590
## 0.010 2 1.0 0.8 200 0.7247350 0.06241380
## 0.010 2 1.0 0.9 25 0.7434739 0.03866645
## 0.010 2 1.0 0.9 50 0.7380629 0.04298614
## 0.010 2 1.0 0.9 100 0.7314323 0.05132298
## 0.010 2 1.0 0.9 200 0.7248900 0.06164328
## 0.010 2 1.0 1.0 25 0.7436973 0.03398111
## 0.010 2 1.0 1.0 50 0.7383531 0.03896411
## 0.010 2 1.0 1.0 100 0.7316552 0.05000766
## 0.010 2 1.0 1.0 200 0.7249458 0.06156257
## 0.010 3 0.8 0.8 25 0.7415025 0.05718598
## 0.010 3 0.8 0.8 50 0.7346917 0.06064198
## 0.010 3 0.8 0.8 100 0.7268742 0.06520439
## 0.010 3 0.8 0.8 200 0.7207088 0.07042110
## 0.010 3 0.8 0.9 25 0.7414604 0.05503369
## 0.010 3 0.8 0.9 50 0.7345305 0.05914869
## 0.010 3 0.8 0.9 100 0.7268407 0.06397249
## 0.010 3 0.8 0.9 200 0.7207848 0.07020457
## 0.010 3 0.8 1.0 25 0.7410377 0.05475732
## 0.010 3 0.8 1.0 50 0.7339658 0.05875021
## 0.010 3 0.8 1.0 100 0.7256083 0.06677022
## 0.010 3 0.8 1.0 200 0.7194196 0.07414805
## 0.010 3 0.9 0.8 25 0.7412730 0.05706242
## 0.010 3 0.9 0.8 50 0.7344614 0.06022107
## 0.010 3 0.9 0.8 100 0.7266325 0.06558272
## 0.010 3 0.9 0.8 200 0.7205201 0.07097266
## 0.010 3 0.9 0.9 25 0.7411565 0.05492089
## 0.010 3 0.9 0.9 50 0.7341190 0.05966007
## 0.010 3 0.9 0.9 100 0.7261936 0.06559892
## 0.010 3 0.9 0.9 200 0.7201335 0.07175611
## 0.010 3 0.9 1.0 25 0.7408537 0.05283177
## 0.010 3 0.9 1.0 50 0.7336606 0.05831720
## 0.010 3 0.9 1.0 100 0.7251413 0.06790347
## 0.010 3 0.9 1.0 200 0.7192260 0.07465551
## 0.010 3 1.0 0.8 25 0.7411687 0.05599938
## 0.010 3 1.0 0.8 50 0.7343726 0.05918153
## 0.010 3 1.0 0.8 100 0.7266468 0.06454017
## 0.010 3 1.0 0.8 200 0.7208628 0.06948139
## 0.010 3 1.0 0.9 25 0.7408461 0.05606467
## 0.010 3 1.0 0.9 50 0.7338687 0.05948457
## 0.010 3 1.0 0.9 100 0.7259815 0.06577193
## 0.010 3 1.0 0.9 200 0.7198581 0.07219228
## 0.010 3 1.0 1.0 25 0.7408857 0.04881559
## 0.010 3 1.0 1.0 50 0.7336884 0.05650114
## 0.010 3 1.0 1.0 100 0.7250992 0.06743905
## 0.010 3 1.0 1.0 200 0.7191595 0.07443204
## 0.025 1 0.8 0.8 25 0.7398640 0.03174343
## 0.025 1 0.8 0.8 50 0.7359196 0.03485465
## 0.025 1 0.8 0.8 100 0.7327535 0.03936470
## 0.025 1 0.8 0.8 200 0.7295324 0.04542392
## 0.025 1 0.8 0.9 25 0.7397966 0.03067528
## 0.025 1 0.8 0.9 50 0.7361637 0.03312115
## 0.025 1 0.8 0.9 100 0.7329987 0.03854144
## 0.025 1 0.8 0.9 200 0.7298392 0.04443605
## 0.025 1 0.8 1.0 25 0.7395672 0.03112148
## 0.025 1 0.8 1.0 50 0.7363708 0.03168643
## 0.025 1 0.8 1.0 100 0.7333384 0.03758263
## 0.025 1 0.8 1.0 200 0.7299466 0.04503658
## 0.025 1 0.9 0.8 25 0.7397399 0.03161994
## 0.025 1 0.9 0.8 50 0.7361351 0.03360841
## 0.025 1 0.9 0.8 100 0.7326535 0.03953405
## 0.025 1 0.9 0.8 200 0.7292538 0.04595656
## 0.025 1 0.9 0.9 25 0.7397698 0.03065454
## 0.025 1 0.9 0.9 50 0.7360715 0.03314625
## 0.025 1 0.9 0.9 100 0.7328656 0.03874164
## 0.025 1 0.9 0.9 200 0.7295370 0.04531622
## 0.025 1 0.9 1.0 25 0.7396269 0.03080441
## 0.025 1 0.9 1.0 50 0.7363716 0.03174890
## 0.025 1 0.9 1.0 100 0.7333625 0.03750323
## 0.025 1 0.9 1.0 200 0.7299705 0.04494608
## 0.025 1 1.0 0.8 25 0.7397813 0.03103207
## 0.025 1 1.0 0.8 50 0.7360626 0.03356110
## 0.025 1 1.0 0.8 100 0.7326542 0.03927125
## 0.025 1 1.0 0.8 200 0.7293122 0.04556484
## 0.025 1 1.0 0.9 25 0.7397511 0.03037796
## 0.025 1 1.0 0.9 50 0.7361643 0.03259598
## 0.025 1 1.0 0.9 100 0.7329862 0.03801625
## 0.025 1 1.0 0.9 200 0.7296489 0.04510326
## 0.025 1 1.0 1.0 25 0.7396463 0.03061977
## 0.025 1 1.0 1.0 50 0.7363727 0.03175424
## 0.025 1 1.0 1.0 100 0.7333671 0.03748244
## 0.025 1 1.0 1.0 200 0.7299592 0.04501166
## 0.025 2 0.8 0.8 25 0.7359175 0.04829239
## 0.025 2 0.8 0.8 50 0.7293980 0.05488223
## 0.025 2 0.8 0.8 100 0.7235337 0.06318084
## 0.025 2 0.8 0.8 200 0.7198732 0.06934634
## 0.025 2 0.8 0.9 25 0.7359808 0.04521715
## 0.025 2 0.8 0.9 50 0.7292771 0.05456905
## 0.025 2 0.8 0.9 100 0.7237371 0.06226773
## 0.025 2 0.8 0.9 200 0.7196480 0.06934592
## 0.025 2 0.8 1.0 25 0.7362286 0.04283906
## 0.025 2 0.8 1.0 50 0.7294339 0.05378094
## 0.025 2 0.8 1.0 100 0.7234826 0.06383922
## 0.025 2 0.8 1.0 200 0.7192235 0.07113368
## 0.025 2 0.9 0.8 25 0.7358054 0.04780652
## 0.025 2 0.9 0.8 50 0.7291640 0.05532316
## 0.025 2 0.9 0.8 100 0.7235885 0.06264769
## 0.025 2 0.9 0.8 200 0.7201456 0.06823839
## 0.025 2 0.9 0.9 25 0.7359605 0.04545875
## 0.025 2 0.9 0.9 50 0.7290096 0.05568758
## 0.025 2 0.9 0.9 100 0.7233536 0.06376930
## 0.025 2 0.9 0.9 200 0.7192639 0.07078679
## 0.025 2 0.9 1.0 25 0.7362895 0.04187607
## 0.025 2 0.9 1.0 50 0.7292383 0.05441957
## 0.025 2 0.9 1.0 100 0.7233821 0.06404301
## 0.025 2 0.9 1.0 200 0.7192163 0.07090910
## 0.025 2 1.0 0.8 25 0.7360213 0.04627732
## 0.025 2 1.0 0.8 50 0.7293023 0.05450432
## 0.025 2 1.0 0.8 100 0.7230847 0.06439852
## 0.025 2 1.0 0.8 200 0.7194865 0.07033088
## 0.025 2 1.0 0.9 25 0.7357696 0.04574066
## 0.025 2 1.0 0.9 50 0.7291129 0.05475754
## 0.025 2 1.0 0.9 100 0.7232726 0.06399596
## 0.025 2 1.0 0.9 200 0.7196236 0.06957911
## 0.025 2 1.0 1.0 25 0.7363841 0.04111737
## 0.025 2 1.0 1.0 50 0.7291125 0.05471604
## 0.025 2 1.0 1.0 100 0.7231591 0.06454913
## 0.025 2 1.0 1.0 200 0.7188752 0.07185645
## 0.025 3 0.8 0.8 25 0.7329493 0.05594279
## 0.025 3 0.8 0.8 50 0.7257060 0.06186515
## 0.025 3 0.8 0.8 100 0.7208867 0.06725017
## 0.025 3 0.8 0.8 200 0.7204407 0.06848578
## 0.025 3 0.8 0.9 25 0.7321161 0.05890478
## 0.025 3 0.8 0.9 50 0.7246131 0.06528793
## 0.025 3 0.8 0.9 100 0.7193994 0.07169468
## 0.025 3 0.8 0.9 200 0.7186079 0.07257280
## 0.025 3 0.8 1.0 25 0.7311699 0.06062955
## 0.025 3 0.8 1.0 50 0.7229965 0.06990937
## 0.025 3 0.8 1.0 100 0.7182151 0.07511660
## 0.025 3 0.8 1.0 200 0.7173730 0.07566650
## 0.025 3 0.9 0.8 25 0.7320640 0.05973024
## 0.025 3 0.9 0.8 50 0.7246955 0.06515221
## 0.025 3 0.9 0.8 100 0.7198208 0.07044974
## 0.025 3 0.9 0.8 200 0.7194618 0.07109143
## 0.025 3 0.9 0.9 25 0.7315511 0.06024815
## 0.025 3 0.9 0.9 50 0.7238837 0.06737809
## 0.025 3 0.9 0.9 100 0.7191884 0.07201699
## 0.025 3 0.9 0.9 200 0.7189337 0.07233622
## 0.025 3 0.9 1.0 25 0.7310599 0.05950368
## 0.025 3 0.9 1.0 50 0.7225743 0.07153373
## 0.025 3 0.9 1.0 100 0.7177715 0.07665885
## 0.025 3 0.9 1.0 200 0.7171871 0.07645175
## 0.025 3 1.0 0.8 25 0.7318110 0.05930090
## 0.025 3 1.0 0.8 50 0.7241859 0.06603597
## 0.025 3 1.0 0.8 100 0.7193324 0.07160252
## 0.025 3 1.0 0.8 200 0.7195811 0.07111932
## 0.025 3 1.0 0.9 25 0.7315209 0.06012641
## 0.025 3 1.0 0.9 50 0.7236113 0.06816646
## 0.025 3 1.0 0.9 100 0.7190960 0.07244928
## 0.025 3 1.0 0.9 200 0.7183750 0.07356326
## 0.025 3 1.0 1.0 25 0.7310253 0.05871792
## 0.025 3 1.0 1.0 50 0.7225036 0.07101894
## 0.025 3 1.0 1.0 100 0.7178622 0.07591490
## 0.025 3 1.0 1.0 200 0.7176284 0.07537026
## 0.050 1 0.8 0.8 25 0.7359159 0.03384268
## 0.050 1 0.8 0.8 50 0.7325556 0.03907845
## 0.050 1 0.8 0.8 100 0.7293310 0.04559788
## 0.050 1 0.8 0.8 200 0.7266265 0.05150110
## 0.050 1 0.8 0.9 25 0.7360755 0.03247682
## 0.050 1 0.8 0.9 50 0.7327289 0.03886245
## 0.050 1 0.8 0.9 100 0.7299035 0.04380953
## 0.050 1 0.8 0.9 200 0.7267588 0.05091966
## 0.050 1 0.8 1.0 25 0.7363181 0.03170145
## 0.050 1 0.8 1.0 50 0.7332962 0.03757366
## 0.050 1 0.8 1.0 100 0.7298447 0.04519935
## 0.050 1 0.8 1.0 200 0.7265708 0.05172160
## 0.050 1 0.9 0.8 25 0.7360776 0.03302807
## 0.050 1 0.9 0.8 50 0.7328405 0.03891328
## 0.050 1 0.9 0.8 100 0.7294514 0.04538669
## 0.050 1 0.9 0.8 200 0.7265107 0.05215364
## 0.050 1 0.9 0.9 25 0.7361541 0.03244312
## 0.050 1 0.9 0.9 50 0.7330244 0.03764722
## 0.050 1 0.9 0.9 100 0.7296565 0.04479078
## 0.050 1 0.9 0.9 200 0.7269075 0.05078052
## 0.050 1 0.9 1.0 25 0.7363430 0.03158160
## 0.050 1 0.9 1.0 50 0.7333353 0.03740560
## 0.050 1 0.9 1.0 100 0.7298964 0.04502422
## 0.050 1 0.9 1.0 200 0.7265691 0.05174604
## 0.050 1 1.0 0.8 25 0.7359681 0.03375922
## 0.050 1 1.0 0.8 50 0.7324958 0.03945449
## 0.050 1 1.0 0.8 100 0.7294300 0.04542075
## 0.050 1 1.0 0.8 200 0.7267332 0.05132253
## 0.050 1 1.0 0.9 25 0.7360936 0.03223173
## 0.050 1 1.0 0.9 50 0.7328146 0.03918295
## 0.050 1 1.0 0.9 100 0.7298148 0.04437708
## 0.050 1 1.0 0.9 200 0.7267605 0.05068723
## 0.050 1 1.0 1.0 25 0.7363400 0.03163449
## 0.050 1 1.0 1.0 50 0.7333270 0.03754977
## 0.050 1 1.0 1.0 100 0.7298896 0.04508538
## 0.050 1 1.0 1.0 200 0.7265541 0.05177949
## 0.050 2 0.8 0.8 25 0.7291471 0.05468782
## 0.050 2 0.8 0.8 50 0.7232623 0.06381732
## 0.050 2 0.8 0.8 100 0.7200262 0.06880772
## 0.050 2 0.8 0.8 200 0.7217482 0.06812425
## 0.050 2 0.8 0.9 25 0.7295422 0.05294143
## 0.050 2 0.8 0.9 50 0.7240888 0.06078002
## 0.050 2 0.8 0.9 100 0.7201266 0.06818119
## 0.050 2 0.8 0.9 200 0.7215726 0.06756941
## 0.050 2 0.8 1.0 25 0.7291860 0.05415861
## 0.050 2 0.8 1.0 50 0.7233450 0.06370318
## 0.050 2 0.8 1.0 100 0.7191478 0.07079784
## 0.050 2 0.8 1.0 200 0.7200042 0.06968325
## 0.050 2 0.9 0.8 25 0.7291376 0.05370494
## 0.050 2 0.9 0.8 50 0.7232261 0.06341169
## 0.050 2 0.9 0.8 100 0.7201768 0.06838261
## 0.050 2 0.9 0.8 200 0.7222330 0.06735931
## 0.050 2 0.9 0.9 25 0.7291188 0.05424690
## 0.050 2 0.9 0.9 50 0.7233212 0.06370283
## 0.050 2 0.9 0.9 100 0.7194963 0.07024806
## 0.050 2 0.9 0.9 200 0.7215406 0.06766445
## 0.050 2 0.9 1.0 25 0.7292072 0.05359406
## 0.050 2 0.9 1.0 50 0.7234198 0.06309068
## 0.050 2 0.9 1.0 100 0.7190629 0.07110252
## 0.050 2 0.9 1.0 200 0.7204076 0.06889267
## 0.050 2 1.0 0.8 25 0.7292873 0.05416183
## 0.050 2 1.0 0.8 50 0.7233210 0.06357963
## 0.050 2 1.0 0.8 100 0.7200507 0.06915592
## 0.050 2 1.0 0.8 200 0.7220334 0.06742147
## 0.050 2 1.0 0.9 25 0.7290023 0.05516981
## 0.050 2 1.0 0.9 50 0.7228322 0.06537930
## 0.050 2 1.0 0.9 100 0.7190780 0.07119611
## 0.050 2 1.0 0.9 200 0.7216824 0.06751047
## 0.050 2 1.0 1.0 25 0.7290690 0.05432083
## 0.050 2 1.0 1.0 50 0.7231131 0.06444255
## 0.050 2 1.0 1.0 100 0.7188153 0.07176208
## 0.050 2 1.0 1.0 200 0.7200545 0.06980961
## 0.050 3 0.8 0.8 25 0.7255268 0.06188258
## 0.050 3 0.8 0.8 50 0.7206993 0.06793503
## 0.050 3 0.8 0.8 100 0.7210440 0.06729371
## 0.050 3 0.8 0.8 200 0.7274507 0.06184755
## 0.050 3 0.8 0.9 25 0.7243429 0.06522788
## 0.050 3 0.8 0.9 50 0.7200913 0.06925911
## 0.050 3 0.8 0.9 100 0.7196832 0.07011926
## 0.050 3 0.8 0.9 200 0.7256641 0.06405410
## 0.050 3 0.8 1.0 25 0.7230851 0.06937071
## 0.050 3 0.8 1.0 50 0.7183396 0.07497723
## 0.050 3 0.8 1.0 100 0.7174911 0.07554482
## 0.050 3 0.8 1.0 200 0.7223252 0.07020146
## 0.050 3 0.9 0.8 25 0.7249524 0.06301305
## 0.050 3 0.9 0.8 50 0.7203350 0.06829099
## 0.050 3 0.9 0.8 100 0.7208799 0.06817422
## 0.050 3 0.9 0.8 200 0.7264592 0.06406250
## 0.050 3 0.9 0.9 25 0.7237536 0.06761085
## 0.050 3 0.9 0.9 50 0.7186742 0.07338951
## 0.050 3 0.9 0.9 100 0.7188480 0.07239465
## 0.050 3 0.9 0.9 200 0.7234955 0.06860695
## 0.050 3 0.9 1.0 25 0.7226222 0.07026966
## 0.050 3 0.9 1.0 50 0.7181543 0.07529307
## 0.050 3 0.9 1.0 100 0.7176311 0.07540595
## 0.050 3 0.9 1.0 200 0.7229204 0.06935891
## 0.050 3 1.0 0.8 25 0.7247192 0.06354241
## 0.050 3 1.0 0.8 50 0.7201882 0.06904779
## 0.050 3 1.0 0.8 100 0.7205430 0.06893092
## 0.050 3 1.0 0.8 200 0.7262775 0.06463681
## 0.050 3 1.0 0.9 25 0.7243217 0.06441599
## 0.050 3 1.0 0.9 50 0.7194213 0.07082137
## 0.050 3 1.0 0.9 100 0.7193630 0.07125793
## 0.050 3 1.0 0.9 200 0.7254355 0.06579141
## 0.050 3 1.0 1.0 25 0.7225112 0.07034519
## 0.050 3 1.0 1.0 50 0.7179141 0.07585588
## 0.050 3 1.0 1.0 100 0.7174869 0.07580786
## 0.050 3 1.0 1.0 200 0.7230767 0.06962026
## MAE
## 0.5660954
## 0.5634735
## 0.5612175
## 0.5592745
## 0.5660134
## 0.5633563
## 0.5612984
## 0.5595259
## 0.5658778
## 0.5632911
## 0.5615557
## 0.5598893
## 0.5661042
## 0.5635007
## 0.5612774
## 0.5592543
## 0.5659780
## 0.5633674
## 0.5613573
## 0.5594395
## 0.5658906
## 0.5633017
## 0.5615586
## 0.5598953
## 0.5660610
## 0.5634501
## 0.5613031
## 0.5592301
## 0.5660076
## 0.5634273
## 0.5614075
## 0.5595304
## 0.5659382
## 0.5633233
## 0.5615584
## 0.5598961
## 0.5650986
## 0.5613988
## 0.5572303
## 0.5527972
## 0.5651374
## 0.5615994
## 0.5575069
## 0.5529490
## 0.5652834
## 0.5618966
## 0.5578192
## 0.5530661
## 0.5650957
## 0.5615037
## 0.5573393
## 0.5526214
## 0.5652131
## 0.5617554
## 0.5574861
## 0.5528046
## 0.5653517
## 0.5620012
## 0.5578449
## 0.5528898
## 0.5650124
## 0.5614205
## 0.5571903
## 0.5525362
## 0.5652274
## 0.5617477
## 0.5574706
## 0.5526691
## 0.5654812
## 0.5621063
## 0.5577925
## 0.5527374
## 0.5636382
## 0.5590376
## 0.5538504
## 0.5496763
## 0.5636191
## 0.5589359
## 0.5539799
## 0.5499951
## 0.5633255
## 0.5586867
## 0.5532308
## 0.5492831
## 0.5634140
## 0.5588437
## 0.5536718
## 0.5495879
## 0.5633144
## 0.5586982
## 0.5534380
## 0.5493733
## 0.5632418
## 0.5585664
## 0.5528617
## 0.5490292
## 0.5633535
## 0.5587797
## 0.5536717
## 0.5498637
## 0.5631498
## 0.5585512
## 0.5532639
## 0.5491392
## 0.5632669
## 0.5585918
## 0.5528041
## 0.5489298
## 0.5627558
## 0.5606488
## 0.5586226
## 0.5561358
## 0.5626627
## 0.5608542
## 0.5587385
## 0.5561798
## 0.5625628
## 0.5610902
## 0.5591039
## 0.5563818
## 0.5626770
## 0.5607903
## 0.5585934
## 0.5559777
## 0.5626585
## 0.5607605
## 0.5586762
## 0.5560267
## 0.5626003
## 0.5610851
## 0.5591363
## 0.5564094
## 0.5627172
## 0.5608270
## 0.5585389
## 0.5559569
## 0.5626978
## 0.5608840
## 0.5587719
## 0.5560842
## 0.5626226
## 0.5610940
## 0.5591294
## 0.5563885
## 0.5602275
## 0.5559338
## 0.5517098
## 0.5498814
## 0.5604610
## 0.5560130
## 0.5518227
## 0.5496223
## 0.5608117
## 0.5562010
## 0.5518045
## 0.5494775
## 0.5600947
## 0.5557757
## 0.5517329
## 0.5498760
## 0.5604892
## 0.5556861
## 0.5517315
## 0.5493794
## 0.5608521
## 0.5560597
## 0.5517904
## 0.5495043
## 0.5603579
## 0.5558313
## 0.5515477
## 0.5496186
## 0.5603098
## 0.5557462
## 0.5515233
## 0.5495380
## 0.5609295
## 0.5559201
## 0.5515264
## 0.5491921
## 0.5580628
## 0.5530616
## 0.5501242
## 0.5507636
## 0.5574398
## 0.5523608
## 0.5491305
## 0.5495578
## 0.5569543
## 0.5513127
## 0.5484529
## 0.5487316
## 0.5573662
## 0.5523800
## 0.5492382
## 0.5503469
## 0.5571018
## 0.5518560
## 0.5489576
## 0.5497410
## 0.5569248
## 0.5511288
## 0.5483160
## 0.5488015
## 0.5574221
## 0.5522508
## 0.5492779
## 0.5502237
## 0.5570879
## 0.5517130
## 0.5489740
## 0.5494333
## 0.5569091
## 0.5509617
## 0.5483448
## 0.5491856
## 0.5605979
## 0.5584458
## 0.5559616
## 0.5547165
## 0.5608154
## 0.5586260
## 0.5563178
## 0.5545854
## 0.5610433
## 0.5591162
## 0.5563040
## 0.5541575
## 0.5607887
## 0.5587134
## 0.5559463
## 0.5546829
## 0.5608367
## 0.5588605
## 0.5561165
## 0.5546530
## 0.5610840
## 0.5591160
## 0.5563249
## 0.5541567
## 0.5606545
## 0.5583830
## 0.5559431
## 0.5547976
## 0.5608575
## 0.5586592
## 0.5563152
## 0.5547096
## 0.5610655
## 0.5591198
## 0.5563336
## 0.5541181
## 0.5558216
## 0.5519810
## 0.5500987
## 0.5528968
## 0.5561511
## 0.5521364
## 0.5498408
## 0.5522534
## 0.5560976
## 0.5517744
## 0.5494355
## 0.5509341
## 0.5556451
## 0.5518129
## 0.5500765
## 0.5535022
## 0.5556699
## 0.5516041
## 0.5494016
## 0.5524121
## 0.5559954
## 0.5517098
## 0.5493870
## 0.5513058
## 0.5558321
## 0.5515302
## 0.5497386
## 0.5529440
## 0.5558516
## 0.5515224
## 0.5493691
## 0.5525654
## 0.5558607
## 0.5514407
## 0.5491500
## 0.5511637
## 0.5528612
## 0.5497463
## 0.5511313
## 0.5572107
## 0.5521728
## 0.5495393
## 0.5502688
## 0.5561725
## 0.5513949
## 0.5487951
## 0.5492756
## 0.5535464
## 0.5526391
## 0.5498907
## 0.5516929
## 0.5571748
## 0.5518582
## 0.5490953
## 0.5500203
## 0.5543283
## 0.5510738
## 0.5487034
## 0.5491006
## 0.5542253
## 0.5522603
## 0.5497699
## 0.5508803
## 0.5566527
## 0.5522488
## 0.5495352
## 0.5501827
## 0.5558500
## 0.5508901
## 0.5483508
## 0.5491580
## 0.5543238
##
## Tuning parameter 'gamma' was held constant at a value of 0
## Tuning
## parameter 'min_child_weight' was held constant at a value of 20
## RMSE was used to select the optimal model using the smallest value.
## The final values used for the model were nrounds = 200, max_depth = 3, eta
## = 0.025, gamma = 0, colsample_bytree = 0.9, min_child_weight = 20
## and subsample = 1.plot(xgbFit2)
physical
library(caret)
library(xgboost)
library(plyr)
library(doParallel)
library(pdp)
set.seed (1)
physicalanalytic=analyticwrace[-c(1,2,4)]
nc = parallel::detectCores()
cl = makePSOCKcluster(nc-1) # Set number of cores equal to machine number minus one
registerDoParallel(cl) #Set up parallel
inTraining = createDataPartition(physicalanalytic$physicaldif, p = .75, list = FALSE)
training = physicalanalytic[ inTraining,]
testing = physicalanalytic[-inTraining,]
fitControl = trainControl(method = "repeatedcv",
number = 10,
repeats = 10,
allowParallel=TRUE
)
xgbGrid3 = expand.grid(nrounds = c(25, 50, 100, 200), #200, 300
max_depth = c(1, 2, 3), #2, 4, 6
eta = c(0.01, 0.025, 0.05), # 0.05, 0.075
gamma = 0,
colsample_bytree = c(0.8, 0.9, 1), #6, 7, 8
min_child_weight = 20,
subsample = c(0.8, 0.9, 1 )) #0.9, 1
xgbFit3 = train(physicaldif ~ ., data = training,
method = "xgbTree",
trControl = fitControl,
tuneGrid = xgbGrid3,
nthread=1,
verbosity = 0
)
stopCluster(cl)
plot(varImp(xgbFit3)) 
vi=varImp(xgbFit3)
vi$importancexgbFit3## eXtreme Gradient Boosting
##
## 1472 samples
## 18 predictor
##
## No pre-processing
## Resampling: Cross-Validated (10 fold, repeated 10 times)
## Summary of sample sizes: 1326, 1325, 1324, 1325, 1325, 1325, ...
## Resampling results across tuning parameters:
##
## eta max_depth colsample_bytree subsample nrounds RMSE Rsquared
## 0.010 1 0.8 0.8 25 0.7837146 0.04800744
## 0.010 1 0.8 0.8 50 0.7562863 0.05330051
## 0.010 1 0.8 0.8 100 0.7275095 0.05663763
## 0.010 1 0.8 0.8 200 0.7108579 0.06111826
## 0.010 1 0.8 0.9 25 0.7837957 0.04684621
## 0.010 1 0.8 0.9 50 0.7563780 0.05165502
## 0.010 1 0.8 0.9 100 0.7277013 0.05544508
## 0.010 1 0.8 0.9 200 0.7114383 0.05887140
## 0.010 1 0.8 1.0 25 0.7840093 0.04409868
## 0.010 1 0.8 1.0 50 0.7565575 0.05131004
## 0.010 1 0.8 1.0 100 0.7279343 0.05487598
## 0.010 1 0.8 1.0 200 0.7117593 0.05792696
## 0.010 1 0.9 0.8 25 0.7833123 0.04973267
## 0.010 1 0.9 0.8 50 0.7557858 0.05413690
## 0.010 1 0.9 0.8 100 0.7271086 0.05677382
## 0.010 1 0.9 0.8 200 0.7108925 0.06037146
## 0.010 1 0.9 0.9 25 0.7834399 0.04822430
## 0.010 1 0.9 0.9 50 0.7558821 0.05234269
## 0.010 1 0.9 0.9 100 0.7271267 0.05619870
## 0.010 1 0.9 0.9 200 0.7111799 0.05946040
## 0.010 1 0.9 1.0 25 0.7836183 0.04610793
## 0.010 1 0.9 1.0 50 0.7560254 0.05215379
## 0.010 1 0.9 1.0 100 0.7273823 0.05542631
## 0.010 1 0.9 1.0 200 0.7117201 0.05798750
## 0.010 1 1.0 0.8 25 0.7830306 0.05076580
## 0.010 1 1.0 0.8 50 0.7552849 0.05460594
## 0.010 1 1.0 0.8 100 0.7267789 0.05685442
## 0.010 1 1.0 0.8 200 0.7107703 0.06075408
## 0.010 1 1.0 0.9 25 0.7830938 0.04902784
## 0.010 1 1.0 0.9 50 0.7552948 0.05389986
## 0.010 1 1.0 0.9 100 0.7268514 0.05617397
## 0.010 1 1.0 0.9 200 0.7111588 0.05942294
## 0.010 1 1.0 1.0 25 0.7831268 0.04851153
## 0.010 1 1.0 1.0 50 0.7553438 0.05375330
## 0.010 1 1.0 1.0 100 0.7271020 0.05557415
## 0.010 1 1.0 1.0 200 0.7116577 0.05816523
## 0.010 2 0.8 0.8 25 0.7814485 0.06383180
## 0.010 2 0.8 0.8 50 0.7526925 0.06895625
## 0.010 2 0.8 0.8 100 0.7218843 0.07486635
## 0.010 2 0.8 0.8 200 0.7023372 0.08310986
## 0.010 2 0.8 0.9 25 0.7814739 0.06063197
## 0.010 2 0.8 0.9 50 0.7527857 0.06544896
## 0.010 2 0.8 0.9 100 0.7220151 0.07336480
## 0.010 2 0.8 0.9 200 0.7025717 0.08176314
## 0.010 2 0.8 1.0 25 0.7813432 0.05839248
## 0.010 2 0.8 1.0 50 0.7528231 0.06281371
## 0.010 2 0.8 1.0 100 0.7220492 0.07227783
## 0.010 2 0.8 1.0 200 0.7034420 0.07873328
## 0.010 2 0.9 0.8 25 0.7810862 0.06442543
## 0.010 2 0.9 0.8 50 0.7521576 0.06946787
## 0.010 2 0.9 0.8 100 0.7212556 0.07615166
## 0.010 2 0.9 0.8 200 0.7017855 0.08413511
## 0.010 2 0.9 0.9 25 0.7811911 0.06135565
## 0.010 2 0.9 0.9 50 0.7523652 0.06672163
## 0.010 2 0.9 0.9 100 0.7216983 0.07315227
## 0.010 2 0.9 0.9 200 0.7025868 0.08088723
## 0.010 2 0.9 1.0 25 0.7810877 0.05738694
## 0.010 2 0.9 1.0 50 0.7525316 0.06288309
## 0.010 2 0.9 1.0 100 0.7219011 0.07209869
## 0.010 2 0.9 1.0 200 0.7035240 0.07837960
## 0.010 2 1.0 0.8 25 0.7809999 0.06194277
## 0.010 2 1.0 0.8 50 0.7521677 0.06686627
## 0.010 2 1.0 0.8 100 0.7212780 0.07453226
## 0.010 2 1.0 0.8 200 0.7020864 0.08213205
## 0.010 2 1.0 0.9 25 0.7808977 0.06029703
## 0.010 2 1.0 0.9 50 0.7520598 0.06513859
## 0.010 2 1.0 0.9 100 0.7215099 0.07251404
## 0.010 2 1.0 0.9 200 0.7026105 0.08033192
## 0.010 2 1.0 1.0 25 0.7808181 0.05597279
## 0.010 2 1.0 1.0 50 0.7522065 0.06245151
## 0.010 2 1.0 1.0 100 0.7219742 0.07081008
## 0.010 2 1.0 1.0 200 0.7036347 0.07783277
## 0.010 3 0.8 0.8 25 0.7799342 0.07361890
## 0.010 3 0.8 0.8 50 0.7500172 0.07759433
## 0.010 3 0.8 0.8 100 0.7180653 0.08276141
## 0.010 3 0.8 0.8 200 0.6989514 0.08794232
## 0.010 3 0.8 0.9 25 0.7797266 0.07296022
## 0.010 3 0.8 0.9 50 0.7500270 0.07520381
## 0.010 3 0.8 0.9 100 0.7181865 0.08093147
## 0.010 3 0.8 0.9 200 0.6990128 0.08725168
## 0.010 3 0.8 1.0 25 0.7799725 0.06499837
## 0.010 3 0.8 1.0 50 0.7505269 0.06852292
## 0.010 3 0.8 1.0 100 0.7188957 0.07639155
## 0.010 3 0.8 1.0 200 0.7000718 0.08326645
## 0.010 3 0.9 0.8 25 0.7798513 0.07113961
## 0.010 3 0.9 0.8 50 0.7498042 0.07638401
## 0.010 3 0.9 0.8 100 0.7179738 0.08153956
## 0.010 3 0.9 0.8 200 0.6988616 0.08775741
## 0.010 3 0.9 0.9 25 0.7797438 0.06736233
## 0.010 3 0.9 0.9 50 0.7499622 0.07182765
## 0.010 3 0.9 0.9 100 0.7181994 0.07940395
## 0.010 3 0.9 0.9 200 0.6993312 0.08539354
## 0.010 3 0.9 1.0 25 0.7799488 0.05881711
## 0.010 3 0.9 1.0 50 0.7506549 0.06411352
## 0.010 3 0.9 1.0 100 0.7191130 0.07422433
## 0.010 3 0.9 1.0 200 0.7003407 0.08218725
## 0.010 3 1.0 0.8 25 0.7794939 0.06896848
## 0.010 3 1.0 0.8 50 0.7493851 0.07510722
## 0.010 3 1.0 0.8 100 0.7175369 0.08170266
## 0.010 3 1.0 0.8 200 0.6986252 0.08776194
## 0.010 3 1.0 0.9 25 0.7795425 0.06542360
## 0.010 3 1.0 0.9 50 0.7498293 0.07008112
## 0.010 3 1.0 0.9 100 0.7180491 0.07851146
## 0.010 3 1.0 0.9 200 0.6992678 0.08520929
## 0.010 3 1.0 1.0 25 0.7798797 0.05437887
## 0.010 3 1.0 1.0 50 0.7507650 0.06067801
## 0.010 3 1.0 1.0 100 0.7192524 0.07260044
## 0.010 3 1.0 1.0 200 0.7007291 0.08064296
## 0.025 1 0.8 0.8 25 0.7461878 0.05441922
## 0.025 1 0.8 0.8 50 0.7202990 0.05763469
## 0.025 1 0.8 0.8 100 0.7085855 0.06278294
## 0.025 1 0.8 0.8 200 0.7037277 0.06959581
## 0.025 1 0.8 0.9 25 0.7462936 0.05272757
## 0.025 1 0.8 0.9 50 0.7204389 0.05654790
## 0.025 1 0.8 0.9 100 0.7089283 0.06101069
## 0.025 1 0.8 0.9 200 0.7044966 0.06729586
## 0.025 1 0.8 1.0 25 0.7464809 0.05309346
## 0.025 1 0.8 1.0 50 0.7207207 0.05589368
## 0.025 1 0.8 1.0 100 0.7095148 0.05929668
## 0.025 1 0.8 1.0 200 0.7053269 0.06539777
## 0.025 1 0.9 0.8 25 0.7456899 0.05484455
## 0.025 1 0.9 0.8 50 0.7197702 0.05826725
## 0.025 1 0.9 0.8 100 0.7083912 0.06278880
## 0.025 1 0.9 0.8 200 0.7037282 0.06926666
## 0.025 1 0.9 0.9 25 0.7457432 0.05359334
## 0.025 1 0.9 0.9 50 0.7200884 0.05691559
## 0.025 1 0.9 0.9 100 0.7089504 0.06054245
## 0.025 1 0.9 0.9 200 0.7045006 0.06700043
## 0.025 1 0.9 1.0 25 0.7458278 0.05385186
## 0.025 1 0.9 1.0 50 0.7203371 0.05585518
## 0.025 1 0.9 1.0 100 0.7094920 0.05933722
## 0.025 1 0.9 1.0 200 0.7053007 0.06545104
## 0.025 1 1.0 0.8 25 0.7452532 0.05530132
## 0.025 1 1.0 0.8 50 0.7197461 0.05777762
## 0.025 1 1.0 0.8 100 0.7083523 0.06262499
## 0.025 1 1.0 0.8 200 0.7035147 0.07021235
## 0.025 1 1.0 0.9 25 0.7451023 0.05500196
## 0.025 1 1.0 0.9 50 0.7199116 0.05668065
## 0.025 1 1.0 0.9 100 0.7087694 0.06104790
## 0.025 1 1.0 0.9 200 0.7043138 0.06746841
## 0.025 1 1.0 1.0 25 0.7452380 0.05464715
## 0.025 1 1.0 1.0 50 0.7202797 0.05589330
## 0.025 1 1.0 1.0 100 0.7094395 0.05950810
## 0.025 1 1.0 1.0 200 0.7053029 0.06542077
## 0.025 2 0.8 0.8 25 0.7420450 0.06989460
## 0.025 2 0.8 0.8 50 0.7137700 0.07674192
## 0.025 2 0.8 0.8 100 0.6995862 0.08354643
## 0.025 2 0.8 0.8 200 0.6953515 0.08843059
## 0.025 2 0.8 0.9 25 0.7420896 0.06803667
## 0.025 2 0.8 0.9 50 0.7138343 0.07526241
## 0.025 2 0.8 0.9 100 0.6995805 0.08296858
## 0.025 2 0.8 0.9 200 0.6952936 0.08872923
## 0.025 2 0.8 1.0 25 0.7422876 0.06547568
## 0.025 2 0.8 1.0 50 0.7142306 0.07437280
## 0.025 2 0.8 1.0 100 0.7004466 0.08094045
## 0.025 2 0.8 1.0 200 0.6967898 0.08427140
## 0.025 2 0.9 0.8 25 0.7413409 0.07139857
## 0.025 2 0.9 0.8 50 0.7133420 0.07713418
## 0.025 2 0.9 0.8 100 0.6988575 0.08521960
## 0.025 2 0.9 0.8 200 0.6948181 0.08993728
## 0.025 2 0.9 0.9 25 0.7417310 0.06768293
## 0.025 2 0.9 0.9 50 0.7136125 0.07507193
## 0.025 2 0.9 0.9 100 0.6997726 0.08198733
## 0.025 2 0.9 0.9 200 0.6955540 0.08770558
## 0.025 2 0.9 1.0 25 0.7418062 0.06614006
## 0.025 2 0.9 1.0 50 0.7141930 0.07318877
## 0.025 2 0.9 1.0 100 0.7005987 0.08009151
## 0.025 2 0.9 1.0 200 0.6970151 0.08362545
## 0.025 2 1.0 0.8 25 0.7414539 0.06856980
## 0.025 2 1.0 0.8 50 0.7132868 0.07631021
## 0.025 2 1.0 0.8 100 0.6987634 0.08533573
## 0.025 2 1.0 0.8 200 0.6948353 0.08980753
## 0.025 2 1.0 0.9 25 0.7414406 0.06699679
## 0.025 2 1.0 0.9 50 0.7134556 0.07524391
## 0.025 2 1.0 0.9 100 0.6994834 0.08318766
## 0.025 2 1.0 0.9 200 0.6954224 0.08825097
## 0.025 2 1.0 1.0 25 0.7415941 0.06568263
## 0.025 2 1.0 1.0 50 0.7141177 0.07311231
## 0.025 2 1.0 1.0 100 0.7007122 0.07983489
## 0.025 2 1.0 1.0 200 0.6972190 0.08316670
## 0.025 3 0.8 0.8 25 0.7392929 0.07486151
## 0.025 3 0.8 0.8 50 0.7099213 0.08339697
## 0.025 3 0.8 0.8 100 0.6965972 0.08778161
## 0.025 3 0.8 0.8 200 0.6943844 0.09079357
## 0.025 3 0.8 0.9 25 0.7393709 0.07383493
## 0.025 3 0.8 0.9 50 0.7101327 0.08202735
## 0.025 3 0.8 0.9 100 0.6969484 0.08671144
## 0.025 3 0.8 0.9 200 0.6947961 0.08923108
## 0.025 3 0.8 1.0 25 0.7395461 0.07051144
## 0.025 3 0.8 1.0 50 0.7105934 0.07932535
## 0.025 3 0.8 1.0 100 0.6976688 0.08456125
## 0.025 3 0.8 1.0 200 0.6959228 0.08582803
## 0.025 3 0.9 0.8 25 0.7388091 0.07620548
## 0.025 3 0.9 0.8 50 0.7095945 0.08281795
## 0.025 3 0.9 0.8 100 0.6968880 0.08708287
## 0.025 3 0.9 0.8 200 0.6950886 0.08948978
## 0.025 3 0.9 0.9 25 0.7391629 0.07275251
## 0.025 3 0.9 0.9 50 0.7099030 0.08126887
## 0.025 3 0.9 0.9 100 0.6968128 0.08687300
## 0.025 3 0.9 0.9 200 0.6949952 0.08899456
## 0.025 3 0.9 1.0 25 0.7399652 0.06574697
## 0.025 3 0.9 1.0 50 0.7110049 0.07656403
## 0.025 3 0.9 1.0 100 0.6982008 0.08294603
## 0.025 3 0.9 1.0 200 0.6966978 0.08427111
## 0.025 3 1.0 0.8 25 0.7385971 0.07573011
## 0.025 3 1.0 0.8 50 0.7095942 0.08268364
## 0.025 3 1.0 0.8 100 0.6962888 0.08852351
## 0.025 3 1.0 0.8 200 0.6944862 0.09076390
## 0.025 3 1.0 0.9 25 0.7385936 0.07404976
## 0.025 3 1.0 0.9 50 0.7096337 0.08134778
## 0.025 3 1.0 0.9 100 0.6966985 0.08712333
## 0.025 3 1.0 0.9 200 0.6948320 0.08957144
## 0.025 3 1.0 1.0 25 0.7399046 0.06426895
## 0.025 3 1.0 1.0 50 0.7110930 0.07559997
## 0.025 3 1.0 1.0 100 0.6983200 0.08217104
## 0.025 3 1.0 1.0 200 0.6971024 0.08336244
## 0.050 1 0.8 0.8 25 0.7201069 0.05698773
## 0.050 1 0.8 0.8 50 0.7085523 0.06143763
## 0.050 1 0.8 0.8 100 0.7038372 0.06896412
## 0.050 1 0.8 0.8 200 0.7008385 0.07480426
## 0.050 1 0.8 0.9 25 0.7200957 0.05664500
## 0.050 1 0.8 0.9 50 0.7088879 0.06059004
## 0.050 1 0.8 0.9 100 0.7044225 0.06707589
## 0.050 1 0.8 0.9 200 0.7011258 0.07399484
## 0.050 1 0.8 1.0 25 0.7203907 0.05599131
## 0.050 1 0.8 1.0 50 0.7094321 0.05939761
## 0.050 1 0.8 1.0 100 0.7053013 0.06541700
## 0.050 1 0.8 1.0 200 0.7024045 0.07031008
## 0.050 1 0.9 0.8 25 0.7199067 0.05608620
## 0.050 1 0.9 0.8 50 0.7086589 0.06105452
## 0.050 1 0.9 0.8 100 0.7038372 0.06839008
## 0.050 1 0.9 0.8 200 0.7011584 0.07387638
## 0.050 1 0.9 0.9 25 0.7198164 0.05644590
## 0.050 1 0.9 0.9 50 0.7087629 0.06082857
## 0.050 1 0.9 0.9 100 0.7043082 0.06786957
## 0.050 1 0.9 0.9 200 0.7010507 0.07401924
## 0.050 1 0.9 1.0 25 0.7200313 0.05578348
## 0.050 1 0.9 1.0 50 0.7094260 0.05931738
## 0.050 1 0.9 1.0 100 0.7052805 0.06550326
## 0.050 1 0.9 1.0 200 0.7023517 0.07050167
## 0.050 1 1.0 0.8 25 0.7195674 0.05675904
## 0.050 1 1.0 0.8 50 0.7083701 0.06248062
## 0.050 1 1.0 0.8 100 0.7037798 0.06894165
## 0.050 1 1.0 0.8 200 0.7007236 0.07552183
## 0.050 1 1.0 0.9 25 0.7197305 0.05629736
## 0.050 1 1.0 0.9 50 0.7087885 0.06114677
## 0.050 1 1.0 0.9 100 0.7040994 0.06833315
## 0.050 1 1.0 0.9 200 0.7012043 0.07348256
## 0.050 1 1.0 1.0 25 0.7199204 0.05588367
## 0.050 1 1.0 1.0 50 0.7094274 0.05932097
## 0.050 1 1.0 1.0 100 0.7052721 0.06553412
## 0.050 1 1.0 1.0 200 0.7023786 0.07047116
## 0.050 2 0.8 0.8 25 0.7136257 0.07499754
## 0.050 2 0.8 0.8 50 0.6992249 0.08374929
## 0.050 2 0.8 0.8 100 0.6948591 0.08993161
## 0.050 2 0.8 0.8 200 0.6950666 0.09147580
## 0.050 2 0.8 0.9 25 0.7134729 0.07472953
## 0.050 2 0.8 0.9 50 0.6993870 0.08368175
## 0.050 2 0.8 0.9 100 0.6950743 0.08926268
## 0.050 2 0.8 0.9 200 0.6939494 0.09303675
## 0.050 2 0.8 1.0 25 0.7142700 0.07242752
## 0.050 2 0.8 1.0 50 0.7004592 0.08034002
## 0.050 2 0.8 1.0 100 0.6967677 0.08412404
## 0.050 2 0.8 1.0 200 0.6955220 0.08790966
## 0.050 2 0.9 0.8 25 0.7136425 0.07410553
## 0.050 2 0.9 0.8 50 0.6996872 0.08225151
## 0.050 2 0.9 0.8 100 0.6954847 0.08792471
## 0.050 2 0.9 0.8 200 0.6960560 0.08875766
## 0.050 2 0.9 0.9 25 0.7133701 0.07537729
## 0.050 2 0.9 0.9 50 0.6996085 0.08227252
## 0.050 2 0.9 0.9 100 0.6954884 0.08778463
## 0.050 2 0.9 0.9 200 0.6941502 0.09253959
## 0.050 2 0.9 1.0 25 0.7138119 0.07329809
## 0.050 2 0.9 1.0 50 0.7005778 0.08007524
## 0.050 2 0.9 1.0 100 0.6971343 0.08350187
## 0.050 2 0.9 1.0 200 0.6957840 0.08773202
## 0.050 2 1.0 0.8 25 0.7123637 0.07763918
## 0.050 2 1.0 0.8 50 0.6991379 0.08376718
## 0.050 2 1.0 0.8 100 0.6953812 0.08832490
## 0.050 2 1.0 0.8 200 0.6953792 0.09020144
## 0.050 2 1.0 0.9 25 0.7129986 0.07519489
## 0.050 2 1.0 0.9 50 0.6995188 0.08275951
## 0.050 2 1.0 0.9 100 0.6957456 0.08750794
## 0.050 2 1.0 0.9 200 0.6949909 0.09099278
## 0.050 2 1.0 1.0 25 0.7138034 0.07283170
## 0.050 2 1.0 1.0 50 0.7005320 0.08017116
## 0.050 2 1.0 1.0 100 0.6972024 0.08332420
## 0.050 2 1.0 1.0 200 0.6957682 0.08775479
## 0.050 3 0.8 0.8 25 0.7097825 0.08141631
## 0.050 3 0.8 0.8 50 0.6967640 0.08747004
## 0.050 3 0.8 0.8 100 0.6948279 0.09005810
## 0.050 3 0.8 0.8 200 0.6989833 0.08689295
## 0.050 3 0.8 0.9 25 0.7095672 0.08228020
## 0.050 3 0.8 0.9 50 0.6966849 0.08719752
## 0.050 3 0.8 0.9 100 0.6948084 0.08961238
## 0.050 3 0.8 0.9 200 0.6975622 0.08887500
## 0.050 3 0.8 1.0 25 0.7104148 0.07806882
## 0.050 3 0.8 1.0 50 0.6979692 0.08333325
## 0.050 3 0.8 1.0 100 0.6962587 0.08537318
## 0.050 3 0.8 1.0 200 0.6979215 0.08633618
## 0.050 3 0.9 0.8 25 0.7094338 0.08237861
## 0.050 3 0.9 0.8 50 0.6965143 0.08771945
## 0.050 3 0.9 0.8 100 0.6951732 0.08933460
## 0.050 3 0.9 0.8 200 0.6995345 0.08569968
## 0.050 3 0.9 0.9 25 0.7097597 0.07997174
## 0.050 3 0.9 0.9 50 0.6968717 0.08638830
## 0.050 3 0.9 0.9 100 0.6950418 0.08913310
## 0.050 3 0.9 0.9 200 0.6981049 0.08801393
## 0.050 3 0.9 1.0 25 0.7103472 0.07740771
## 0.050 3 0.9 1.0 50 0.6979958 0.08300883
## 0.050 3 0.9 1.0 100 0.6967150 0.08441687
## 0.050 3 0.9 1.0 200 0.6984543 0.08580700
## 0.050 3 1.0 0.8 25 0.7089484 0.08345135
## 0.050 3 1.0 0.8 50 0.6968240 0.08656327
## 0.050 3 1.0 0.8 100 0.6952987 0.08826475
## 0.050 3 1.0 0.8 200 0.6998403 0.08544207
## 0.050 3 1.0 0.9 25 0.7098222 0.07911465
## 0.050 3 1.0 0.9 50 0.6965864 0.08674142
## 0.050 3 1.0 0.9 100 0.6946451 0.08958279
## 0.050 3 1.0 0.9 200 0.6989071 0.08625497
## 0.050 3 1.0 1.0 25 0.7108448 0.07465036
## 0.050 3 1.0 1.0 50 0.6987049 0.08086119
## 0.050 3 1.0 1.0 100 0.6974635 0.08266611
## 0.050 3 1.0 1.0 200 0.6995147 0.08367333
## MAE
## 0.5874671
## 0.5650062
## 0.5426107
## 0.5313993
## 0.5875533
## 0.5650427
## 0.5427960
## 0.5318239
## 0.5876984
## 0.5650475
## 0.5428876
## 0.5322745
## 0.5873889
## 0.5649553
## 0.5426728
## 0.5315182
## 0.5874788
## 0.5650033
## 0.5428085
## 0.5318468
## 0.5875718
## 0.5649843
## 0.5429301
## 0.5323179
## 0.5872931
## 0.5648854
## 0.5427467
## 0.5315975
## 0.5873684
## 0.5648694
## 0.5428231
## 0.5318622
## 0.5873940
## 0.5648400
## 0.5430045
## 0.5322778
## 0.5865207
## 0.5631862
## 0.5388341
## 0.5250619
## 0.5866781
## 0.5633887
## 0.5391102
## 0.5254386
## 0.5865769
## 0.5635106
## 0.5392832
## 0.5263084
## 0.5864554
## 0.5630682
## 0.5386849
## 0.5248761
## 0.5866592
## 0.5633213
## 0.5391014
## 0.5254433
## 0.5867025
## 0.5636293
## 0.5394346
## 0.5263349
## 0.5865542
## 0.5632351
## 0.5388457
## 0.5251462
## 0.5866205
## 0.5633644
## 0.5392403
## 0.5255330
## 0.5867759
## 0.5636731
## 0.5396259
## 0.5263427
## 0.5853973
## 0.5612967
## 0.5359123
## 0.5223748
## 0.5853942
## 0.5614946
## 0.5364103
## 0.5225411
## 0.5856317
## 0.5619613
## 0.5371024
## 0.5235912
## 0.5855186
## 0.5612673
## 0.5360581
## 0.5222271
## 0.5856075
## 0.5616965
## 0.5366173
## 0.5228841
## 0.5858099
## 0.5622955
## 0.5374915
## 0.5238687
## 0.5853931
## 0.5612154
## 0.5360143
## 0.5221510
## 0.5855863
## 0.5617318
## 0.5365918
## 0.5228543
## 0.5859623
## 0.5626031
## 0.5377124
## 0.5242158
## 0.5570375
## 0.5374449
## 0.5303503
## 0.5272117
## 0.5570832
## 0.5375143
## 0.5305500
## 0.5278394
## 0.5570803
## 0.5377442
## 0.5311035
## 0.5285792
## 0.5569448
## 0.5372913
## 0.5302853
## 0.5271223
## 0.5570765
## 0.5375837
## 0.5306936
## 0.5278787
## 0.5569945
## 0.5377853
## 0.5311214
## 0.5285656
## 0.5569266
## 0.5373929
## 0.5302240
## 0.5271129
## 0.5568530
## 0.5375286
## 0.5306023
## 0.5277172
## 0.5568740
## 0.5378345
## 0.5310915
## 0.5285819
## 0.5544349
## 0.5329141
## 0.5234211
## 0.5210376
## 0.5547617
## 0.5330012
## 0.5235429
## 0.5212305
## 0.5549781
## 0.5334824
## 0.5243438
## 0.5221953
## 0.5543237
## 0.5328143
## 0.5229411
## 0.5206256
## 0.5546205
## 0.5330298
## 0.5237651
## 0.5215949
## 0.5549015
## 0.5336023
## 0.5244302
## 0.5223112
## 0.5545049
## 0.5331238
## 0.5231785
## 0.5208348
## 0.5546566
## 0.5331572
## 0.5235480
## 0.5212950
## 0.5550044
## 0.5336262
## 0.5244243
## 0.5223588
## 0.5523030
## 0.5297949
## 0.5207640
## 0.5200720
## 0.5526992
## 0.5302529
## 0.5213782
## 0.5207513
## 0.5530003
## 0.5307976
## 0.5221221
## 0.5217614
## 0.5522512
## 0.5298746
## 0.5211513
## 0.5209125
## 0.5527814
## 0.5303962
## 0.5214942
## 0.5209626
## 0.5535879
## 0.5314598
## 0.5225821
## 0.5221870
## 0.5523996
## 0.5299246
## 0.5207385
## 0.5201768
## 0.5525165
## 0.5303640
## 0.5215686
## 0.5212337
## 0.5537716
## 0.5315747
## 0.5228385
## 0.5227729
## 0.5373221
## 0.5302108
## 0.5272331
## 0.5248672
## 0.5373101
## 0.5305602
## 0.5277667
## 0.5251607
## 0.5374531
## 0.5310310
## 0.5285839
## 0.5261971
## 0.5373951
## 0.5305406
## 0.5273153
## 0.5250926
## 0.5372465
## 0.5305085
## 0.5277260
## 0.5251528
## 0.5374795
## 0.5310996
## 0.5285916
## 0.5261889
## 0.5372971
## 0.5304209
## 0.5272950
## 0.5247001
## 0.5375190
## 0.5306015
## 0.5276242
## 0.5251895
## 0.5375975
## 0.5311083
## 0.5285870
## 0.5261879
## 0.5327833
## 0.5234111
## 0.5208372
## 0.5208777
## 0.5329000
## 0.5234171
## 0.5211130
## 0.5199630
## 0.5333953
## 0.5244430
## 0.5223606
## 0.5212011
## 0.5328429
## 0.5237314
## 0.5214798
## 0.5217421
## 0.5331333
## 0.5239205
## 0.5216291
## 0.5205370
## 0.5333789
## 0.5243878
## 0.5224085
## 0.5212044
## 0.5321107
## 0.5231743
## 0.5210147
## 0.5211514
## 0.5328784
## 0.5237480
## 0.5217034
## 0.5205759
## 0.5334115
## 0.5244365
## 0.5224740
## 0.5211151
## 0.5300206
## 0.5214320
## 0.5207947
## 0.5237562
## 0.5298929
## 0.5212448
## 0.5208504
## 0.5225147
## 0.5308129
## 0.5223554
## 0.5220456
## 0.5228853
## 0.5297865
## 0.5213958
## 0.5210515
## 0.5239070
## 0.5302724
## 0.5216704
## 0.5210200
## 0.5231409
## 0.5310499
## 0.5227762
## 0.5226395
## 0.5237166
## 0.5295422
## 0.5213803
## 0.5208988
## 0.5236220
## 0.5306808
## 0.5218447
## 0.5210805
## 0.5236039
## 0.5314964
## 0.5230497
## 0.5227153
## 0.5235535
##
## Tuning parameter 'gamma' was held constant at a value of 0
## Tuning
## parameter 'min_child_weight' was held constant at a value of 20
## RMSE was used to select the optimal model using the smallest value.
## The final values used for the model were nrounds = 200, max_depth = 2, eta
## = 0.05, gamma = 0, colsample_bytree = 0.8, min_child_weight = 20 and
## subsample = 0.9.plot(xgbFit3)
fairpoor
library(caret)
library(xgboost)
library(plyr)
library(doParallel)
library(pdp)
set.seed (1)
fairpooranalytic=analyticwrace[-c(1,2,3)]
nc = parallel::detectCores()
cl = makePSOCKcluster(nc-1) # Set number of cores equal to machine number minus one
registerDoParallel(cl) #Set up parallel
inTraining = createDataPartition(fairpooranalytic$fairpoordif, p = .75, list = FALSE)
training = fairpooranalytic[ inTraining,]
testing = fairpooranalytic[-inTraining,]
fitControl = trainControl(method = "repeatedcv",
number = 10,
repeats = 10,
allowParallel=TRUE
)
xgbGrid4 = expand.grid(nrounds = c(25, 50, 100, 200), #200, 300
max_depth = c(1, 2, 3), #2, 4, 6
eta = c(0.01, 0.025, 0.05), # 0.05, 0.075
gamma = 0,
colsample_bytree = c(0.8, 0.9, 1), #6, 7, 8
min_child_weight = 20,
subsample = c(0.8, 0.9, 1 )) #0.9, 1
xgbFit4 = train(fairpoordif ~ ., data = training,
method = "xgbTree",
trControl = fitControl,
tuneGrid = xgbGrid4,
nthread=1,
verbosity = 0
)
stopCluster(cl)
plot(varImp(xgbFit4))
vi=varImp(xgbFit4)
vi$importancexgbFit4## eXtreme Gradient Boosting
##
## 1472 samples
## 18 predictor
##
## No pre-processing
## Resampling: Cross-Validated (10 fold, repeated 10 times)
## Summary of sample sizes: 1326, 1325, 1324, 1325, 1325, 1325, ...
## Resampling results across tuning parameters:
##
## eta max_depth colsample_bytree subsample nrounds RMSE Rsquared
## 0.010 1 0.8 0.8 25 3.544687 0.08735137
## 0.010 1 0.8 0.8 50 3.512375 0.08869168
## 0.010 1 0.8 0.8 100 3.475542 0.09419756
## 0.010 1 0.8 0.8 200 3.433456 0.10888492
## 0.010 1 0.8 0.9 25 3.544909 0.08678922
## 0.010 1 0.8 0.9 50 3.512554 0.08705024
## 0.010 1 0.8 0.9 100 3.478247 0.09032653
## 0.010 1 0.8 0.9 200 3.438276 0.10491572
## 0.010 1 0.8 1.0 25 3.543212 0.08805377
## 0.010 1 0.8 1.0 50 3.511661 0.08608347
## 0.010 1 0.8 1.0 100 3.480286 0.08725411
## 0.010 1 0.8 1.0 200 3.444670 0.09999669
## 0.010 1 0.9 0.8 25 3.540885 0.08652979
## 0.010 1 0.9 0.8 50 3.508868 0.08693702
## 0.010 1 0.9 0.8 100 3.473858 0.09303224
## 0.010 1 0.9 0.8 200 3.432468 0.10835652
## 0.010 1 0.9 0.9 25 3.540803 0.08558750
## 0.010 1 0.9 0.9 50 3.508237 0.08569462
## 0.010 1 0.9 0.9 100 3.475703 0.08972421
## 0.010 1 0.9 0.9 200 3.437569 0.10459866
## 0.010 1 0.9 1.0 25 3.540147 0.08689532
## 0.010 1 0.9 1.0 50 3.508014 0.08487940
## 0.010 1 0.9 1.0 100 3.479267 0.08567158
## 0.010 1 0.9 1.0 200 3.445273 0.09940067
## 0.010 1 1.0 0.8 25 3.538238 0.08457026
## 0.010 1 1.0 0.8 50 3.505427 0.08528586
## 0.010 1 1.0 0.8 100 3.473095 0.09130978
## 0.010 1 1.0 0.8 200 3.432025 0.10829221
## 0.010 1 1.0 0.9 25 3.537565 0.08415648
## 0.010 1 1.0 0.9 50 3.504824 0.08441076
## 0.010 1 1.0 0.9 100 3.474803 0.08897158
## 0.010 1 1.0 0.9 200 3.437166 0.10439151
## 0.010 1 1.0 1.0 25 3.537167 0.08392793
## 0.010 1 1.0 1.0 50 3.505501 0.08248994
## 0.010 1 1.0 1.0 100 3.479595 0.08400291
## 0.010 1 1.0 1.0 200 3.445719 0.09904055
## 0.010 2 0.8 0.8 25 3.531806 0.10527624
## 0.010 2 0.8 0.8 50 3.488813 0.11023093
## 0.010 2 0.8 0.8 100 3.433299 0.11996669
## 0.010 2 0.8 0.8 200 3.377313 0.13310502
## 0.010 2 0.8 0.9 25 3.532522 0.10208074
## 0.010 2 0.8 0.9 50 3.490334 0.10637928
## 0.010 2 0.8 0.9 100 3.435792 0.11697854
## 0.010 2 0.8 0.9 200 3.380221 0.13144312
## 0.010 2 0.8 1.0 25 3.534360 0.09545046
## 0.010 2 0.8 1.0 50 3.494358 0.09877800
## 0.010 2 0.8 1.0 100 3.442137 0.11038576
## 0.010 2 0.8 1.0 200 3.384012 0.12879987
## 0.010 2 0.9 0.8 25 3.528795 0.10375287
## 0.010 2 0.9 0.8 50 3.484420 0.10866369
## 0.010 2 0.9 0.8 100 3.428446 0.12037309
## 0.010 2 0.9 0.8 200 3.375781 0.13284697
## 0.010 2 0.9 0.9 25 3.530255 0.09893047
## 0.010 2 0.9 0.9 50 3.486998 0.10432533
## 0.010 2 0.9 0.9 100 3.431925 0.11676387
## 0.010 2 0.9 0.9 200 3.377353 0.13178498
## 0.010 2 0.9 1.0 25 3.531624 0.09242400
## 0.010 2 0.9 1.0 50 3.490189 0.09780550
## 0.010 2 0.9 1.0 100 3.436804 0.11215999
## 0.010 2 0.9 1.0 200 3.382550 0.12857865
## 0.010 2 1.0 0.8 25 3.525698 0.10218387
## 0.010 2 1.0 0.8 50 3.480482 0.10867852
## 0.010 2 1.0 0.8 100 3.426333 0.11937779
## 0.010 2 1.0 0.8 200 3.375028 0.13258079
## 0.010 2 1.0 0.9 25 3.527109 0.09685192
## 0.010 2 1.0 0.9 50 3.483588 0.10231471
## 0.010 2 1.0 0.9 100 3.428408 0.11677905
## 0.010 2 1.0 0.9 200 3.376132 0.13183200
## 0.010 2 1.0 1.0 25 3.529402 0.08901508
## 0.010 2 1.0 1.0 50 3.488085 0.09520418
## 0.010 2 1.0 1.0 100 3.435484 0.11062185
## 0.010 2 1.0 1.0 200 3.381736 0.12896531
## 0.010 3 0.8 0.8 25 3.518275 0.12856584
## 0.010 3 0.8 0.8 50 3.464088 0.13351188
## 0.010 3 0.8 0.8 100 3.400800 0.13781677
## 0.010 3 0.8 0.8 200 3.346654 0.14671902
## 0.010 3 0.8 0.9 25 3.517666 0.12612583
## 0.010 3 0.8 0.9 50 3.463894 0.13125636
## 0.010 3 0.8 0.9 100 3.400008 0.13750859
## 0.010 3 0.8 0.9 200 3.346113 0.14684025
## 0.010 3 0.8 1.0 25 3.516747 0.12342311
## 0.010 3 0.8 1.0 50 3.464574 0.12830097
## 0.010 3 0.8 1.0 100 3.401812 0.13546347
## 0.010 3 0.8 1.0 200 3.348641 0.14483447
## 0.010 3 0.9 0.8 25 3.514925 0.12433953
## 0.010 3 0.9 0.8 50 3.460868 0.12970165
## 0.010 3 0.9 0.8 100 3.398421 0.13571164
## 0.010 3 0.9 0.8 200 3.344724 0.14673321
## 0.010 3 0.9 0.9 25 3.514407 0.12306521
## 0.010 3 0.9 0.9 50 3.460603 0.12829307
## 0.010 3 0.9 0.9 100 3.397023 0.13592855
## 0.010 3 0.9 0.9 200 3.345255 0.14640955
## 0.010 3 0.9 1.0 25 3.514547 0.11645279
## 0.010 3 0.9 1.0 50 3.462843 0.12233791
## 0.010 3 0.9 1.0 100 3.400414 0.13241100
## 0.010 3 0.9 1.0 200 3.352404 0.14171559
## 0.010 3 1.0 0.8 25 3.511449 0.12237416
## 0.010 3 1.0 0.8 50 3.457438 0.12694209
## 0.010 3 1.0 0.8 100 3.395797 0.13493476
## 0.010 3 1.0 0.8 200 3.343993 0.14632627
## 0.010 3 1.0 0.9 25 3.511877 0.11826545
## 0.010 3 1.0 0.9 50 3.457885 0.12455535
## 0.010 3 1.0 0.9 100 3.396309 0.13335411
## 0.010 3 1.0 0.9 200 3.345769 0.14525918
## 0.010 3 1.0 1.0 25 3.512463 0.11020163
## 0.010 3 1.0 1.0 50 3.461426 0.11719114
## 0.010 3 1.0 1.0 100 3.401580 0.12792315
## 0.010 3 1.0 1.0 200 3.354986 0.13963263
## 0.025 1 0.8 0.8 25 3.500686 0.08841126
## 0.025 1 0.8 0.8 50 3.462904 0.09724678
## 0.025 1 0.8 0.8 100 3.419024 0.11386079
## 0.025 1 0.8 0.8 200 3.373503 0.13065341
## 0.025 1 0.8 0.9 25 3.501084 0.08619333
## 0.025 1 0.8 0.9 50 3.467233 0.09323388
## 0.025 1 0.8 0.9 100 3.424269 0.10994696
## 0.025 1 0.8 0.9 200 3.381731 0.12623945
## 0.025 1 0.8 1.0 25 3.501008 0.08596448
## 0.025 1 0.8 1.0 50 3.469397 0.09069366
## 0.025 1 0.8 1.0 100 3.431422 0.10564369
## 0.025 1 0.8 1.0 200 3.394906 0.11964907
## 0.025 1 0.9 0.8 25 3.497861 0.08753001
## 0.025 1 0.9 0.8 50 3.461930 0.09668560
## 0.025 1 0.9 0.8 100 3.417520 0.11433090
## 0.025 1 0.9 0.8 200 3.373546 0.13051537
## 0.025 1 0.9 0.9 25 3.497321 0.08537701
## 0.025 1 0.9 0.9 50 3.463724 0.09388147
## 0.025 1 0.9 0.9 100 3.423374 0.11029125
## 0.025 1 0.9 0.9 200 3.381894 0.12613450
## 0.025 1 0.9 1.0 25 3.497158 0.08444772
## 0.025 1 0.9 1.0 50 3.468517 0.08962616
## 0.025 1 0.9 1.0 100 3.431359 0.10553822
## 0.025 1 0.9 1.0 200 3.394605 0.11983611
## 0.025 1 1.0 0.8 25 3.494427 0.08590261
## 0.025 1 1.0 0.8 50 3.459907 0.09671918
## 0.025 1 1.0 0.8 100 3.415801 0.11506800
## 0.025 1 1.0 0.8 200 3.371259 0.13123934
## 0.025 1 1.0 0.9 25 3.495101 0.08417746
## 0.025 1 1.0 0.9 50 3.464466 0.09245316
## 0.025 1 1.0 0.9 100 3.421871 0.11108161
## 0.025 1 1.0 0.9 200 3.380501 0.12670870
## 0.025 1 1.0 1.0 25 3.495487 0.08213294
## 0.025 1 1.0 1.0 50 3.469778 0.08817079
## 0.025 1 1.0 1.0 100 3.431612 0.10536604
## 0.025 1 1.0 1.0 200 3.394300 0.12006567
## 0.025 2 0.8 0.8 25 3.471187 0.11222410
## 0.025 2 0.8 0.8 50 3.415676 0.12302139
## 0.025 2 0.8 0.8 100 3.364816 0.13591158
## 0.025 2 0.8 0.8 200 3.333876 0.14645341
## 0.025 2 0.8 0.9 25 3.473341 0.10800306
## 0.025 2 0.8 0.9 50 3.416764 0.12140742
## 0.025 2 0.8 0.9 100 3.366831 0.13446406
## 0.025 2 0.8 0.9 200 3.333569 0.14632679
## 0.025 2 0.8 1.0 25 3.478606 0.10071180
## 0.025 2 0.8 1.0 50 3.421313 0.11741079
## 0.025 2 0.8 1.0 100 3.372240 0.13125756
## 0.025 2 0.8 1.0 200 3.342600 0.14213746
## 0.025 2 0.9 0.8 25 3.466681 0.11092929
## 0.025 2 0.9 0.8 50 3.411508 0.12277496
## 0.025 2 0.9 0.8 100 3.363817 0.13555721
## 0.025 2 0.9 0.8 200 3.332151 0.14690700
## 0.025 2 0.9 0.9 25 3.469147 0.10736189
## 0.025 2 0.9 0.9 50 3.413009 0.12154259
## 0.025 2 0.9 0.9 100 3.366127 0.13410947
## 0.025 2 0.9 0.9 200 3.335920 0.14513533
## 0.025 2 0.9 1.0 25 3.473743 0.10082170
## 0.025 2 0.9 1.0 50 3.416391 0.11928035
## 0.025 2 0.9 1.0 100 3.371651 0.13124165
## 0.025 2 0.9 1.0 200 3.339994 0.14338234
## 0.025 2 1.0 0.8 25 3.463855 0.11002736
## 0.025 2 1.0 0.8 50 3.407872 0.12432728
## 0.025 2 1.0 0.8 100 3.361299 0.13665446
## 0.025 2 1.0 0.8 200 3.334685 0.14559615
## 0.025 2 1.0 0.9 25 3.466209 0.10566761
## 0.025 2 1.0 0.9 50 3.409403 0.12239264
## 0.025 2 1.0 0.9 100 3.363956 0.13503965
## 0.025 2 1.0 0.9 200 3.332165 0.14700138
## 0.025 2 1.0 1.0 25 3.471838 0.09852070
## 0.025 2 1.0 1.0 50 3.414702 0.11895388
## 0.025 2 1.0 1.0 100 3.371529 0.13122547
## 0.025 2 1.0 1.0 200 3.338938 0.14391350
## 0.025 3 0.8 0.8 25 3.444338 0.13187125
## 0.025 3 0.8 0.8 50 3.381475 0.13962701
## 0.025 3 0.8 0.8 100 3.333123 0.14989699
## 0.025 3 0.8 0.8 200 3.314220 0.15543264
## 0.025 3 0.8 0.9 25 3.442258 0.13239100
## 0.025 3 0.8 0.9 50 3.377392 0.14218801
## 0.025 3 0.8 0.9 100 3.332450 0.15020496
## 0.025 3 0.8 0.9 200 3.313872 0.15546136
## 0.025 3 0.8 1.0 25 3.443686 0.13027430
## 0.025 3 0.8 1.0 50 3.381213 0.13865102
## 0.025 3 0.8 1.0 100 3.336977 0.14769903
## 0.025 3 0.8 1.0 200 3.314910 0.15493653
## 0.025 3 0.9 0.8 25 3.440615 0.12978844
## 0.025 3 0.9 0.8 50 3.380518 0.13723474
## 0.025 3 0.9 0.8 100 3.334609 0.14776891
## 0.025 3 0.9 0.8 200 3.316360 0.15423213
## 0.025 3 0.9 0.9 25 3.438746 0.13032364
## 0.025 3 0.9 0.9 50 3.377427 0.13884331
## 0.025 3 0.9 0.9 100 3.332865 0.14918894
## 0.025 3 0.9 0.9 200 3.315769 0.15465324
## 0.025 3 0.9 1.0 25 3.442802 0.12434145
## 0.025 3 0.9 1.0 50 3.383059 0.13401997
## 0.025 3 0.9 1.0 100 3.339431 0.14595706
## 0.025 3 0.9 1.0 200 3.316573 0.15427566
## 0.025 3 1.0 0.8 25 3.438922 0.12625203
## 0.025 3 1.0 0.8 50 3.379790 0.13590591
## 0.025 3 1.0 0.8 100 3.337290 0.14627498
## 0.025 3 1.0 0.8 200 3.319654 0.15282716
## 0.025 3 1.0 0.9 25 3.436737 0.12687414
## 0.025 3 1.0 0.9 50 3.377982 0.13641260
## 0.025 3 1.0 0.9 100 3.330918 0.15010254
## 0.025 3 1.0 0.9 200 3.312845 0.15610792
## 0.025 3 1.0 1.0 25 3.441490 0.12067769
## 0.025 3 1.0 1.0 50 3.385611 0.13070414
## 0.025 3 1.0 1.0 100 3.342545 0.14379281
## 0.025 3 1.0 1.0 200 3.318989 0.15279309
## 0.050 1 0.8 0.8 25 3.462657 0.09731068
## 0.050 1 0.8 0.8 50 3.417402 0.11543987
## 0.050 1 0.8 0.8 100 3.373867 0.13021511
## 0.050 1 0.8 0.8 200 3.343012 0.14126541
## 0.050 1 0.8 0.9 25 3.466299 0.09281638
## 0.050 1 0.8 0.9 50 3.424102 0.10974971
## 0.050 1 0.8 0.9 100 3.382278 0.12585300
## 0.050 1 0.8 0.9 200 3.349096 0.13851329
## 0.050 1 0.8 1.0 25 3.469247 0.09021280
## 0.050 1 0.8 1.0 50 3.430695 0.10572951
## 0.050 1 0.8 1.0 100 3.394008 0.12003863
## 0.050 1 0.8 1.0 200 3.361518 0.13272906
## 0.050 1 0.9 0.8 25 3.460364 0.09754648
## 0.050 1 0.9 0.8 50 3.416185 0.11466113
## 0.050 1 0.9 0.8 100 3.372633 0.13017370
## 0.050 1 0.9 0.8 200 3.343351 0.14094356
## 0.050 1 0.9 0.9 25 3.464796 0.09329161
## 0.050 1 0.9 0.9 50 3.422158 0.11064263
## 0.050 1 0.9 0.9 100 3.382751 0.12503465
## 0.050 1 0.9 0.9 200 3.348988 0.13830837
## 0.050 1 0.9 1.0 25 3.468269 0.08974065
## 0.050 1 0.9 1.0 50 3.430707 0.10571316
## 0.050 1 0.9 1.0 100 3.393900 0.12008991
## 0.050 1 0.9 1.0 200 3.361438 0.13276326
## 0.050 1 1.0 0.8 25 3.461212 0.09496599
## 0.050 1 1.0 0.8 50 3.417854 0.11305919
## 0.050 1 1.0 0.8 100 3.372471 0.13065597
## 0.050 1 1.0 0.8 200 3.344763 0.14052802
## 0.050 1 1.0 0.9 25 3.463097 0.09263936
## 0.050 1 1.0 0.9 50 3.421468 0.11057428
## 0.050 1 1.0 0.9 100 3.380312 0.12653766
## 0.050 1 1.0 0.9 200 3.348668 0.13848105
## 0.050 1 1.0 1.0 25 3.469372 0.08816275
## 0.050 1 1.0 1.0 50 3.430834 0.10561715
## 0.050 1 1.0 1.0 100 3.393899 0.12014275
## 0.050 1 1.0 1.0 200 3.361294 0.13289423
## 0.050 2 0.8 0.8 25 3.416316 0.12092151
## 0.050 2 0.8 0.8 50 3.366270 0.13433935
## 0.050 2 0.8 0.8 100 3.338722 0.14336562
## 0.050 2 0.8 0.8 200 3.340412 0.14425779
## 0.050 2 0.8 0.9 25 3.414854 0.12161661
## 0.050 2 0.8 0.9 50 3.366915 0.13357464
## 0.050 2 0.8 0.9 100 3.335747 0.14496106
## 0.050 2 0.8 0.9 200 3.335140 0.14622192
## 0.050 2 0.8 1.0 25 3.421970 0.11711891
## 0.050 2 0.8 1.0 50 3.372605 0.13101991
## 0.050 2 0.8 1.0 100 3.341324 0.14274421
## 0.050 2 0.8 1.0 200 3.335230 0.14577603
## 0.050 2 0.9 0.8 25 3.412133 0.12199885
## 0.050 2 0.9 0.8 50 3.364122 0.13493503
## 0.050 2 0.9 0.8 100 3.335899 0.14492103
## 0.050 2 0.9 0.8 200 3.341794 0.14375097
## 0.050 2 0.9 0.9 25 3.411466 0.12236492
## 0.050 2 0.9 0.9 50 3.364663 0.13482289
## 0.050 2 0.9 0.9 100 3.333774 0.14645763
## 0.050 2 0.9 0.9 200 3.330862 0.14859942
## 0.050 2 0.9 1.0 25 3.415866 0.11885681
## 0.050 2 0.9 1.0 50 3.370947 0.13145397
## 0.050 2 0.9 1.0 100 3.338666 0.14410573
## 0.050 2 0.9 1.0 200 3.331648 0.14758508
## 0.050 2 1.0 0.8 25 3.408582 0.12236602
## 0.050 2 1.0 0.8 50 3.361985 0.13582983
## 0.050 2 1.0 0.8 100 3.332894 0.14613840
## 0.050 2 1.0 0.8 200 3.338874 0.14514243
## 0.050 2 1.0 0.9 25 3.409536 0.12143227
## 0.050 2 1.0 0.9 50 3.366567 0.13320012
## 0.050 2 1.0 0.9 100 3.335477 0.14537940
## 0.050 2 1.0 0.9 200 3.334205 0.14717414
## 0.050 2 1.0 1.0 25 3.413992 0.11893250
## 0.050 2 1.0 1.0 50 3.371027 0.13135535
## 0.050 2 1.0 1.0 100 3.338602 0.14412796
## 0.050 2 1.0 1.0 200 3.329954 0.14829606
## 0.050 3 0.8 0.8 25 3.383988 0.13591491
## 0.050 3 0.8 0.8 50 3.335195 0.14846338
## 0.050 3 0.8 0.8 100 3.318431 0.15355888
## 0.050 3 0.8 0.8 200 3.337311 0.14822935
## 0.050 3 0.8 0.9 25 3.380129 0.13842362
## 0.050 3 0.8 0.9 50 3.336160 0.14738247
## 0.050 3 0.8 0.9 100 3.319135 0.15289978
## 0.050 3 0.8 0.9 200 3.335479 0.14799198
## 0.050 3 0.8 1.0 25 3.381255 0.13722820
## 0.050 3 0.8 1.0 50 3.336159 0.14775609
## 0.050 3 0.8 1.0 100 3.315047 0.15527156
## 0.050 3 0.8 1.0 200 3.327219 0.15141488
## 0.050 3 0.9 0.8 25 3.380763 0.13648927
## 0.050 3 0.9 0.8 50 3.335242 0.14758649
## 0.050 3 0.9 0.8 100 3.322562 0.15161858
## 0.050 3 0.9 0.8 200 3.343618 0.14556676
## 0.050 3 0.9 0.9 25 3.378274 0.13766716
## 0.050 3 0.9 0.9 50 3.330453 0.15037780
## 0.050 3 0.9 0.9 100 3.314311 0.15507399
## 0.050 3 0.9 0.9 200 3.332958 0.14943188
## 0.050 3 0.9 1.0 25 3.381964 0.13429897
## 0.050 3 0.9 1.0 50 3.340195 0.14494663
## 0.050 3 0.9 1.0 100 3.318928 0.15281458
## 0.050 3 0.9 1.0 200 3.331636 0.14889548
## 0.050 3 1.0 0.8 25 3.379074 0.13579532
## 0.050 3 1.0 0.8 50 3.337269 0.14626006
## 0.050 3 1.0 0.8 100 3.324185 0.15109440
## 0.050 3 1.0 0.8 200 3.343229 0.14638043
## 0.050 3 1.0 0.9 25 3.376568 0.13659102
## 0.050 3 1.0 0.9 50 3.334388 0.14776516
## 0.050 3 1.0 0.9 100 3.316753 0.15393844
## 0.050 3 1.0 0.9 200 3.336408 0.14862460
## 0.050 3 1.0 1.0 25 3.384292 0.13087612
## 0.050 3 1.0 1.0 50 3.342323 0.14349203
## 0.050 3 1.0 1.0 100 3.317973 0.15344901
## 0.050 3 1.0 1.0 200 3.330641 0.14973630
## MAE
## 2.670402
## 2.644265
## 2.615952
## 2.584517
## 2.670490
## 2.643881
## 2.617254
## 2.587732
## 2.669374
## 2.643272
## 2.618638
## 2.592531
## 2.667193
## 2.641335
## 2.614849
## 2.583626
## 2.667158
## 2.640472
## 2.615380
## 2.587540
## 2.666841
## 2.640409
## 2.617797
## 2.593234
## 2.665253
## 2.638960
## 2.614297
## 2.583392
## 2.664709
## 2.638302
## 2.615276
## 2.587136
## 2.664443
## 2.638873
## 2.618441
## 2.593752
## 2.659702
## 2.626288
## 2.584888
## 2.541571
## 2.660395
## 2.627206
## 2.586990
## 2.544984
## 2.661301
## 2.629523
## 2.591203
## 2.547964
## 2.657639
## 2.623358
## 2.582164
## 2.541049
## 2.658609
## 2.624806
## 2.584427
## 2.542732
## 2.659163
## 2.626891
## 2.588124
## 2.547050
## 2.655420
## 2.620803
## 2.581187
## 2.540153
## 2.656219
## 2.623014
## 2.583142
## 2.542048
## 2.657917
## 2.626347
## 2.588646
## 2.546543
## 2.649823
## 2.607523
## 2.558195
## 2.517620
## 2.649841
## 2.607637
## 2.558134
## 2.518406
## 2.649666
## 2.609071
## 2.561677
## 2.522305
## 2.647767
## 2.605464
## 2.556813
## 2.516732
## 2.647441
## 2.605459
## 2.556936
## 2.518275
## 2.648401
## 2.608602
## 2.561557
## 2.525058
## 2.645564
## 2.603327
## 2.555539
## 2.515298
## 2.646260
## 2.604536
## 2.557909
## 2.519281
## 2.647454
## 2.608790
## 2.563698
## 2.527372
## 2.634966
## 2.606612
## 2.573722
## 2.539968
## 2.634662
## 2.609046
## 2.576972
## 2.546177
## 2.634485
## 2.610404
## 2.582584
## 2.556201
## 2.632661
## 2.605530
## 2.572355
## 2.538984
## 2.632009
## 2.606783
## 2.577217
## 2.546187
## 2.631912
## 2.610014
## 2.582849
## 2.556074
## 2.630631
## 2.604782
## 2.571570
## 2.537993
## 2.630864
## 2.607766
## 2.575778
## 2.544870
## 2.631077
## 2.611368
## 2.583037
## 2.555809
## 2.613767
## 2.571845
## 2.532034
## 2.507800
## 2.614950
## 2.573267
## 2.533949
## 2.508593
## 2.617707
## 2.575938
## 2.538655
## 2.516918
## 2.609943
## 2.568400
## 2.530285
## 2.506264
## 2.611385
## 2.570190
## 2.532857
## 2.510222
## 2.615011
## 2.573393
## 2.538358
## 2.515943
## 2.608874
## 2.566958
## 2.528579
## 2.507722
## 2.610549
## 2.568901
## 2.531913
## 2.507531
## 2.614669
## 2.573182
## 2.538125
## 2.514649
## 2.593360
## 2.544969
## 2.508102
## 2.495581
## 2.590298
## 2.541889
## 2.508525
## 2.496085
## 2.593243
## 2.545944
## 2.512880
## 2.498856
## 2.589876
## 2.543228
## 2.507610
## 2.496195
## 2.589205
## 2.542293
## 2.508196
## 2.497248
## 2.593137
## 2.548303
## 2.515033
## 2.501157
## 2.589390
## 2.543325
## 2.510074
## 2.498981
## 2.588986
## 2.544187
## 2.508100
## 2.495925
## 2.594193
## 2.550717
## 2.517898
## 2.503816
## 2.606272
## 2.572751
## 2.540257
## 2.516331
## 2.607873
## 2.577055
## 2.546329
## 2.521929
## 2.610452
## 2.582200
## 2.555689
## 2.531419
## 2.604895
## 2.572088
## 2.539606
## 2.517342
## 2.608127
## 2.576324
## 2.546495
## 2.521940
## 2.609656
## 2.582135
## 2.555574
## 2.531359
## 2.605101
## 2.572641
## 2.538240
## 2.516363
## 2.607066
## 2.575792
## 2.544493
## 2.521264
## 2.611014
## 2.582436
## 2.555600
## 2.531354
## 2.572514
## 2.533547
## 2.512220
## 2.513138
## 2.570862
## 2.533760
## 2.510462
## 2.510922
## 2.576303
## 2.539135
## 2.517049
## 2.512894
## 2.568190
## 2.531237
## 2.509589
## 2.515149
## 2.568845
## 2.532960
## 2.508801
## 2.507459
## 2.573130
## 2.537870
## 2.514653
## 2.510198
## 2.566593
## 2.530032
## 2.506982
## 2.513337
## 2.568962
## 2.533971
## 2.509308
## 2.510189
## 2.572761
## 2.537947
## 2.514700
## 2.509118
## 2.545687
## 2.509385
## 2.499656
## 2.516010
## 2.544677
## 2.512294
## 2.500406
## 2.514399
## 2.545336
## 2.512108
## 2.498985
## 2.507345
## 2.543681
## 2.510017
## 2.501956
## 2.517481
## 2.544361
## 2.508394
## 2.498998
## 2.513350
## 2.546936
## 2.515224
## 2.501895
## 2.511399
## 2.543350
## 2.509746
## 2.501682
## 2.518434
## 2.542302
## 2.510277
## 2.499817
## 2.514120
## 2.549785
## 2.518794
## 2.503682
## 2.513873
##
## Tuning parameter 'gamma' was held constant at a value of 0
## Tuning
## parameter 'min_child_weight' was held constant at a value of 20
## RMSE was used to select the optimal model using the smallest value.
## The final values used for the model were nrounds = 200, max_depth = 3, eta
## = 0.025, gamma = 0, colsample_bytree = 1, min_child_weight = 20 and
## subsample = 0.9.plot(xgbFit4)
Add a new chunk by clicking the Insert Chunk button on the toolbar or by pressing Cmd+Option+I.
When you save the notebook, an HTML file containing the code and output will be saved alongside it (click the Preview button or press Cmd+Shift+K to preview the HTML file).
The preview shows you a rendered HTML copy of the contents of the editor. Consequently, unlike Knit, Preview does not run any R code chunks. Instead, the output of the chunk when it was last run in the editor is displayed.